Marine diesel engine fault detection method, device and equipment and storage medium

Abstract

The embodiment of the invention discloses a marine diesel engine fault detection method, device and equipment and a storage medium, and relates to the technical field of fault detection processing. The scheme comprises the following steps: acquiring multiple groups of to-be-tested vibration signals of the marine diesel engine; decomposing a plurality of groups of to-be-detected vibration signals of the marine diesel engine by using a symplectic geometric mode decomposition algorithm, fusing by using a multi-mode fusion algorithm to obtain a to-be-detected image set, and 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, whether the marine diesel engine corresponding to the target to-be-detected image has a fault or not is determined, and the to-be-detected image obtained by combining the symplectic geometric mode decomposition algorithm and the multi-mode fusion algorithm is compared with the standard image, so that fault detection can be accurately and efficiently performed on the diesel engine.

Description

Technical Field

[0001] The present application relates to the technical field of fault detection, and in particular to a method, device, equipment and storage medium for detecting faults of a marine diesel engine. Background Art

[0002] Marine diesel engines play a vital role in modern industry. Their high efficiency, wide application and reliability make them an important power source for ships. However, as marine diesel engines work in harsh environments for a long time, failures are inevitable. If the failure is not discovered and handled in time, it may cause significant economic losses at the least, or even cause casualties. Therefore, timely fault detection of marine diesel engines is crucial.

[0003] In related technologies, ship diesel engine faults can be detected through signal analysis and deep learning models. However, since the signals of ship diesel engines are complex, the selection is difficult, and the computational complexity of deep learning models is high. Summary of the invention

[0004] The embodiments of this specification provide a method for detecting marine diesel engine faults to solve the problems existing in the prior art of detecting marine diesel engine faults using signal analysis and deep learning models.

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

[0006] In a first aspect, an embodiment of the present specification provides a method for detecting a fault in a marine diesel engine, comprising:

[0007] Obtain multiple groups of vibration signals to be tested from ship diesel engines;

[0008] Decomposing the plurality of groups of vibration signals to be measured by using a symplectic geometry modal decomposition algorithm to obtain a plurality of modal signals;

[0009] Using a multimodal fusion algorithm to fuse several of the modal signals to obtain a set of images to be tested;

[0010] Determine a first normal similarity between a target image to be tested in the image set to be tested and a first normal image in the standard image set, and a first abnormal similarity between the target image to be tested and a 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 ship diesel engine corresponding to the target image to be tested has a fault.

[0012] In a second aspect, an embodiment of the present specification provides a marine diesel engine fault detection device, comprising:

[0013] An acquisition module, used for acquiring multiple groups of vibration signals to be tested from a ship diesel engine;

[0014] A decomposition module, used for decomposing the plurality of groups of vibration signals to be measured by using a symplectic geometry modal decomposition algorithm to obtain a plurality of modal signals;

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

[0016] A first determination module is used to determine a first normal similarity between a target image to be tested in the image set to be tested and a first normal image in the standard image set, and a first abnormal similarity between the target image to be tested and a first abnormal image in the standard image set;

[0017] The second determination module is configured to determine that a fault exists in the ship diesel engine corresponding to the target image to be tested when it is determined that the first normal similarity is less than the first abnormal similarity.

[0018] In a third aspect, an embodiment of the present specification provides a ship diesel engine fault detection device, comprising a memory, a processor and a computer program stored in the memory, wherein the processor executes the computer program to implement the ship diesel engine fault detection method in scheme one.

[0019] In a fourth aspect, an embodiment of the present specification provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the ship diesel engine fault detection method in scheme one is implemented.

[0020] An embodiment of the present specification realizes the following beneficial effects: multiple groups of vibration signals to be tested of a ship diesel engine are decomposed using a symplectic geometric modal decomposition algorithm, and a set of images to be tested is obtained after being fused using a multimodal fusion algorithm. The similarity between a target image to be tested in the set of images to be tested and an image in a standard image set is calculated to determine whether the ship 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 modal decomposition algorithm with the multimodal fusion algorithm with the standard image, accurate and efficient fault detection of the diesel engine can be achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the embodiments of this specification or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0022] Figure 1A schematic diagram of a process flow of a marine diesel engine fault detection method provided in an embodiment of this specification;

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

[0024] Figure 3 A schematic diagram of comparing a test image set with a standard image set provided in an embodiment of this specification;

[0025] Figure 4 A schematic diagram of the structure of a marine diesel engine fault detection device provided in an embodiment of this specification;

[0026] Figure 5 A structural schematic diagram of a marine diesel engine fault detection device provided in an embodiment of this specification. DETAILED DESCRIPTION

[0027] In order to make the purpose, 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 combination with the specific embodiments of this specification and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of this specification, not all of the embodiments. Based on the embodiments in this specification, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of one or more embodiments of this specification.

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

[0029] A marine diesel engine fault detection method provided in the embodiment of the specification is specifically described in conjunction with the accompanying drawings.

[0030] Figure 1 The following is a flow chart of a method for detecting a marine diesel engine fault provided in an embodiment of this specification. Figure 1 As shown, the process may include the following steps:

[0031] Step 110: Acquire multiple groups of vibration signals to be measured of the ship diesel engine.

[0032] In the embodiments of this specification, an acceleration sensor is used to collect vibration signals of a ship diesel engine in operation, and vibration signals within a preset time period are taken as a group. Multiple groups of vibration signals under different working conditions can be collected.

[0033] Step 120: Decompose the plurality of groups of vibration signals to be measured using a symplectic geometry modal decomposition algorithm to obtain a plurality of modal signals.

[0034] In the embodiment of this specification, symplectic geometric mode decomposition is used to eliminate the influence of noise on the signal to achieve fault feature enhancement. The acquired one-dimensional signal is x={x 1 ,x 2 ,x 3 ,...x n}, n is the one-dimensional signal length, according to Takkens theorem, x is constructed into a matrix X, the matrix X is:

[0035]

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

[0037] The Hamiltonian matrix A can be obtained by performing autocorrelation analysis on the constructed matrix X, where A = X T X, T are matrix transposes. Matrix A is used to construct matrix M. Matrix M is:

[0038]

[0039] After constructing the matrix M, the symplectic orthogonal matrix Q is constructed. The relationship between the matrix Q and the matrix M is:

[0040]

[0041] Among them, B is an upper triangular matrix and R is a real matrix.

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

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

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

[0045] Z i =Q i W i , Z=Z 1 +Z 2 +...+Z k ,

[0046] For the matrix Z i Transform to obtain a one-dimensional time series Y i ,y k Yes i A data point in 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] Perform angular averaging on each matrix to obtain a one-dimensional time series, thereby generating d groups of initial single-signal components Y = [Y 1 , Y 2 ,..., Y d , that is, a number of modal signals.

[0050] Step 130: Use a multi-modal fusion algorithm to fuse the several 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 the 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 of comparing the target image to be measured in the set of images to be measured with the first normal image in the set of standard images, and the first abnormal similarity of the target image to be measured and the first abnormal image in the set of standard images.

[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, the normal image can be an image corresponding to the vibration signal after the normal operation state of the marine diesel engine, and the abnormal image can be an image corresponding to the vibration signal after the fault operation state of the marine diesel engine.

[0055] Compare the similarity of the target image to be measured in the set of images to be measured with the normal image in the set of standard images to obtain the normal similarity, and compare the similarity of the target image to be measured in the set of images to be measured with the abnormal image in the set of standard images 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, each target image in the test image set is compared with the normal image and abnormal image in the standard image set for similarity, and the operating status of the ship 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 can be interchanged according to actual needs, or some steps can be omitted or deleted.

[0059] In the embodiments of the present specification, a symplectic geometric modal decomposition algorithm is used to decompose multiple groups of vibration signals to be tested of a ship diesel engine. After being fused using a multimodal fusion algorithm, a set of images to be tested is obtained. The similarity between a target image to be tested in the set of images to be tested and an image in a standard image set is calculated to determine whether the ship 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 modal decomposition algorithm with 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 The method in this specification also provides some specific implementation plans of the method, which are described below.

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

[0062] Selecting a target modal signal from the plurality of modal signals based on an adaptive maximum spectral entropy method;

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

[0064] In the embodiments of the present specification, the adaptive maximum spectral entropy method may be to calculate the spectral entropy of each modal signal after Fourier transformation, 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 most uncertainty is selected as the target modal signal. The target modal signal is fused into a fused image, which will contain complementary information from different modal signals, improve the comprehensiveness and accuracy of the information, and reduce the redundant data that needs to be screened and processed during the processing.

[0066] Each group of vibration signals to be tested is decomposed to obtain several modal signals, and a preset number of modal signals are selected as target modal signals from the modal signals corresponding to each group of vibration signals to be tested using the adaptive maximum spectral entropy method. The target modal signals corresponding to each group of vibration signals to be tested are fused using a multimodal fusion algorithm to obtain the images to be tested corresponding to each group of vibration signals to be tested after conversion, and all images to be tested are combined into a set of images to be tested.

[0067] Specifically, the best six modal signals are selected as target modal signals. Among the d groups of initial single signal components Y, the six best modal signals Y'=[Y' 1 ,Y' 2 ,Y' 3 ,Y' 4 ,Y' 5 ,Y' 6 ], the formula is:

[0068]

[0069] Among them, F i (k) is the coefficient after Fourier transformation, Y i (n) is the input signal, is a complex term, argmax(S i ) is the maximum numerical index.

[0070] The obtained Y'=[Y' 1 ,Y' 2 ,Y' 3 ,Y' 4 ,Y' 5 ,Y' 6 The data points in each mode in ] are fused through the multimodal fusion algorithm, and the multimodal fusion formula is:

[0071]

[0072] Among them, G = [1, 2, 3, 4, 5, 6], G is the Gth mode, r G (i) is the radius of the i-th data point of the G-th mode on the polar coordinate axis, Y' Gi is the amplitude of the i-th point of the G-th mode Y, Y' Gmin is the minimum amplitude of the one-dimensional time domain signal of G modes, Y' Gmax is the maximum amplitude of the one-dimensional time domain signal of G modes, θ G (i) is the Gth mode rotated clockwise by 60°, φ G (i) is the Gth mode rotated counterclockwise by 60°, and g is the magnification factor.

[0073] In order to quickly and accurately determine the current operating state of the diesel engine, optionally, before determining 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 in the embodiment of this specification, the method may include:

[0074] Acquiring multiple groups of normal vibration signals and multiple groups of abnormal vibration signals of the ship diesel engine;

[0075] Decomposing the plurality of groups of normal vibration signals by using a symplectic geometry mode decomposition algorithm to obtain a plurality of normal mode signals;

[0076] Decomposing the plurality of groups of abnormal vibration signals by using a symplectic geometry mode decomposition algorithm to obtain a plurality of abnormal mode signals;

[0077] Using a multimodal fusion algorithm to fuse a number of the normal modal signals to obtain a normal image set;

[0078] Using a multimodal fusion algorithm to fuse a number of abnormal modal signals to obtain an abnormal image set;

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

[0080] In the embodiments of this specification, a standard image set is pre-constructed to form a benchmark for comparison and analysis.

[0081] Each group of normal vibration signals is decomposed to obtain several normal modal signals, and a preset number of normal modal signals are selected as target normal modal signals from the several normal modal signals corresponding to each group of normal vibration signals using the adaptive maximum spectral entropy method. The target normal modal signals corresponding to each group of normal vibration signals are fused using a multimodal fusion algorithm to obtain the normal images corresponding to each group of normal vibration signals after conversion, and all normal images are combined into a normal image set.

[0082] Each group of abnormal vibration signals is decomposed to obtain several abnormal modal signals, and a preset number of abnormal modal signals are selected as target abnormal modal signals from the several abnormal modal signals corresponding to each group of abnormal vibration signals using the adaptive maximum spectral entropy method. The target abnormal modal signals corresponding to each group of abnormal vibration signals are fused using a multimodal fusion algorithm to obtain the abnormal images corresponding to each group of abnormal vibration signals after conversion, and all abnormal images are combined into an abnormal image set.

[0083] The generated normal images and abnormal images are combined to form a complete standard image set, which contains the vibration characteristic images of the diesel engine in normal and abnormal states, providing a basis for subsequent comparative analysis.

[0084] Figure 2 A schematic diagram of a multimodal fused image provided in an embodiment of this specification.

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

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

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

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

[0089] Comparing the first normal similarity with the second normal similarity to obtain a target normal similarity;

[0090] Comparing the first anomaly similarity with the second anomaly similarity to obtain a target anomaly similarity;

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

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

[0093] The abnormal image set may include several abnormal images, and the target image to be tested is compared with each abnormal image in the abnormal image set to obtain the corresponding abnormal similarity.

[0094] The smaller one of the first normal similarity and the second normal similarity is used as the target normal similarity, and the smallest normal similarity after comparison with the normal image in the normal image set is selected as the target normal similarity.

[0095] The smaller one of the first abnormality similarity and the second abnormality similarity is used as the target abnormality similarity, and the smallest abnormality similarity after comparison with the abnormal image in the abnormal image set is selected as the target abnormality similarity.

[0096] The minimum normal similarity is compared with the minimum abnormal similarity. If the target normal similarity is greater than the target abnormal similarity, it can be considered that the state of the ship diesel engine represented by the target image to be tested is more similar to the normal state. Therefore, it is determined that the operating state of the ship diesel engine corresponding to the target image to be tested is normal.

[0097] If the target normal similarity is less than the target abnormal similarity, it can be considered that the ship diesel engine state represented by the target image to be tested is more similar to the abnormal state, so it is determined that the ship diesel engine operating state corresponding to the target image to be tested has a fault.

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

[0099]

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

[0101] In fault detection, choosing a smaller normal similarity as the target normal similarity means being more sensitive to the difference between the target image to be tested and the normal state. Even tiny differences may be regarded as potential signs of faults, which helps to avoid missing faults.

[0102] By comparing multiple similarity values, it is possible to 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 a smaller value can avoid misjudgments caused by noise interference.

[0103] Figure 3 A schematic diagram of comparing a test image set with a standard image set provided in an embodiment 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 images and abnormal images for comparison, and obtaining more accurate judgment results by comparing similarities, the accuracy and reliability of fault diagnosis are improved. Furthermore, by comparing with different abnormal image sets, the fault type of the ship diesel engine can be determined.

[0106] In practical applications, the symplectic geometric modal decomposition algorithm is used to decompose multiple groups of vibration signals to be tested of ship diesel engines. Based on the adaptive maximum spectral entropy method, the target modal signal is selected from several modal signals. The modal signals are fused using the multimodal fusion algorithm to obtain a set of images to be tested. The similarity of any target image to be tested in the set of images to be tested with the normal image and the abnormal image in the standard image set is calculated respectively, and the minimum normal similarity is compared with the minimum abnormal similarity to determine whether the ship diesel engine corresponding to the target image to be tested has a fault. The image to be tested obtained by combining the symplectic geometric modal decomposition algorithm with the multimodal fusion algorithm is compared with the standard image, thereby realizing adaptive multimodal signal selection, low computational complexity, and realizing multi-scale analysis of complex signals, so that diesel engine fault detection can be performed accurately and efficiently.

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

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

[0109] An acquisition module 402 is used to acquire multiple groups of vibration signals to be measured from a ship diesel engine;

[0110] A decomposition module 404 is used to decompose the plurality of groups of vibration signals to be measured using a symplectic geometry modal decomposition algorithm to obtain a plurality of modal signals;

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

[0112] A first determination module 408 is used to determine a first normal similarity between a target image to be tested in the image set to be tested and a first normal image in the standard image set, and a first abnormal similarity between the target image to be tested and a first abnormal image in the standard image set;

[0113] The second determination module 410 is configured to determine that a fault exists in the ship diesel engine corresponding to the target image to be tested when it is determined that the first normal similarity is less than the first abnormal similarity.

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

[0115] Selecting a target modal signal from the plurality of modal signals based on an adaptive maximum spectral entropy method;

[0116] The target modality 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 to be tested in the image set to be tested and the first normal image in the standard image set in the embodiment of this specification, the device may include:

[0118] An acquisition module, used for acquiring multiple groups of normal vibration signals and multiple groups of abnormal vibration signals of the ship diesel engine;

[0119] A decomposition module, used to decompose the plurality of groups of normal vibration signals using a symplectic geometric modal decomposition algorithm to obtain a plurality of normal modal signals; and to decompose the plurality of groups of abnormal vibration signals using a symplectic geometric modal decomposition algorithm to obtain a plurality of abnormal modal signals;

[0120] A fusion module, used to fuse a plurality of the normal modal signals using a multimodal fusion algorithm to obtain a normal image set; and to fuse a plurality of the abnormal modal signals using a multimodal fusion algorithm to obtain an abnormal image set;

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

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

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

[0124] Comparing the first normal similarity with the second normal similarity to obtain a target normal similarity;

[0125] Comparing the first anomaly similarity with the second anomaly similarity to obtain a target anomaly similarity;

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

[0127] Based on the same idea, the embodiments of this specification also provide a device corresponding to the above method.

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

[0129] A ship diesel engine fault detection device provided in an embodiment of the present specification may include a memory, a processor, and a computer program stored in the memory, and the processor executes the computer program to implement the ship diesel engine fault detection method described in any of the above embodiments.

[0130] An embodiment of the present specification provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the ship diesel engine fault detection method described in any of the above embodiments can be implemented.

[0131] Each embodiment in this specification is described in a progressive manner. The same or similar parts between the embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments. Figure 5 As for the device shown, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0132] In the 1990s, improvements to a technology could be clearly distinguished as hardware improvements (for example, improvements to the circuit structure of diodes, transistors, switches, etc.) or software improvements (improvements to the method flow). However, with the development of technology, many improvements to the method flow today can be regarded as direct improvements to the hardware circuit structure. Designers almost always obtain the corresponding hardware circuit structure by programming the improved method flow into the hardware circuit. Therefore, it cannot be said that an improvement in a method flow cannot be implemented using a hardware entity module. For example, a programmable logic device (PLD) (such as a field programmable gate array (FPGA)) is such an integrated circuit whose logical function is determined by the user's programming of the device. Designers can "integrate" a digital system on a PLD by programming it themselves, without having to ask a chip manufacturer to design and produce a dedicated integrated circuit chip. Moreover, nowadays, instead of manually making integrated circuit chips, this kind of programming is mostly implemented by "logic compiler" software, which is similar to the software compiler used when developing and writing programs, and the original code before compilation must also be written in a specific programming language, which is called hardware description language (HDL). There is not only one HDL, but many kinds, 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, RHDL (Ruby Hardware Description Language), etc. The most commonly used ones are VHDL (Very-High-Speed ​​Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should also know that it is only necessary to program the method flow slightly in the above-mentioned hardware description languages ​​and program it into the integrated circuit, and then it is easy to obtain the hardware circuit that implements the logic method flow.

[0133] The controller can be implemented in any appropriate manner, for example, the controller can take the form of a microprocessor or processor and a computer-readable medium storing a computer-readable program code (such as software or firmware) that can be executed by the (micro)processor, a logic gate, a switch, an application-specific integrated circuit (ASIC), a programmable logic controller, and an embedded microcontroller. Examples of controllers include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320. The memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art also know that in addition to implementing the controller in a purely computer-readable program code manner, the controller can be implemented in the form of a logic gate, a switch, an application-specific integrated circuit, a programmable logic controller, and an embedded microcontroller by logically programming the method steps. Therefore, this controller can be considered as a hardware component, and the devices included therein for implementing various functions can also be regarded as structures within the hardware component. Or even, the devices for implementing various functions can be regarded as both software modules for implementing the method and structures within the hardware component.

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

[0135] For the convenience of description, the above device is described in various units according to their functions. Of course, when implementing the present application, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0136] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented 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] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0138] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0139] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function 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] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0142] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules 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 technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0143] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0144] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

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

[0146] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A method for detecting faults in a marine diesel engine, characterized in that: include: Obtain multiple groups of vibration signals to be tested from ship diesel engines; Decomposing the plurality of groups of vibration signals to be measured by using a symplectic geometry modal decomposition algorithm to obtain a plurality of modal signals; Using a multimodal fusion algorithm to fuse several of the modal signals to obtain a set of images to be tested; Determine a first normal similarity between a target image to be tested in the image set to be tested and a first normal image in the standard image set, and a first abnormal similarity between the target image to be tested and 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 ship diesel engine corresponding to the target image to be tested has a fault.

2. The method according to claim 1, characterized in that The method of fusing a plurality of modal signals using a multimodal fusion algorithm to obtain a set of images to be tested specifically includes: Selecting a target modal signal from the plurality of modal signals based on an adaptive maximum spectral entropy method; The target modality signals are fused using a multimodal fusion algorithm to obtain a set of images to be tested.

3. The method according to claim 1, characterized in that Before determining a first normal similarity between a target image to be tested in the image set to be tested and a first normal image in the standard image set, the method comprises: Acquiring multiple groups of normal vibration signals and multiple groups of abnormal vibration signals of the ship diesel engine; Decomposing the plurality of groups of normal vibration signals by using a symplectic geometry mode decomposition algorithm to obtain a plurality of normal mode signals; Decomposing the plurality of groups of abnormal vibration signals by using a symplectic geometry mode decomposition algorithm to obtain a plurality of abnormal mode signals; Using a multimodal fusion algorithm to fuse a number of the normal modal signals to obtain a normal image set; Using a multimodal fusion algorithm to fuse a number of abnormal modal signals to obtain an abnormal image set; The normal image set and the abnormal image set are combined to obtain the standard image set.

4. The method according to claim 3, characterized in that When it is determined that the first normal similarity is less than the first abnormal similarity, determining that the ship diesel engine corresponding to the target image to be tested has a fault specifically includes: Determine a second normal similarity between the target image to be tested in the image set to be tested and the second normal image in the normal image set, and a second abnormal similarity between the target image to be tested and the 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 anomaly similarity with the second anomaly similarity to obtain a target anomaly similarity; When it is determined that the target normal similarity is less than the target abnormal similarity, it is determined that the ship diesel engine corresponding to the target image to be tested has a fault.

5. A marine diesel engine fault detection device, characterized in that: include: An acquisition module, used for acquiring multiple groups of vibration signals to be tested from a ship diesel engine; A decomposition module, used for decomposing the plurality of groups of vibration signals to be measured by using a symplectic geometry modal decomposition algorithm to obtain a plurality of modal signals; A fusion module, used to fuse several modal signals using a multimodal fusion algorithm to obtain a set of images to be tested; A first determination module is used to determine a first normal similarity between a target image to be tested in the image set to be tested and a first normal image in the standard image set, and a first abnormal similarity between the target image to be tested and a first abnormal image in the standard image set; The second determination module is configured to determine that a fault exists in the ship diesel engine corresponding to the target image to be tested when it is determined that the first normal similarity is less than the first abnormal similarity.

6. The device according to claim 5, characterized in that The method of fusing a plurality of modal signals using a multimodal fusion algorithm to obtain a set of images to be tested specifically includes: Selecting a target modal signal from the plurality of modal signals based on an adaptive maximum spectral entropy method; The target modality signals are fused using a multimodal fusion algorithm to obtain a set of images to be tested.

7. The device according to claim 5, characterized in that Before determining a first normal similarity between a target image to be tested in the image set to be tested and a first normal image in the standard image set, the device comprises: Acquiring multiple groups of normal vibration signals and multiple groups of abnormal vibration signals of the ship diesel engine; Decomposing the plurality of groups of normal vibration signals by using a symplectic geometry mode decomposition algorithm to obtain a plurality of normal mode signals; Decomposing the plurality of groups of abnormal vibration signals by using a symplectic geometry mode decomposition algorithm to obtain a plurality of abnormal mode signals; Using a multimodal fusion algorithm to fuse a number of the normal modal signals to obtain a normal image set; Using a multimodal fusion algorithm to fuse a number of abnormal modal signals to obtain an abnormal image set; The normal image set and the abnormal image set are combined to obtain the standard image set.

8. The device according to claim 7, characterized in that When it is determined that the first normal similarity is less than the first abnormal similarity, determining that the ship diesel engine corresponding to the target image to be tested has a fault specifically includes: Determine a second normal similarity between the target image to be tested in the image set to be tested and the second normal image in the normal image set, and a second abnormal similarity between the target image to be tested and the 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 anomaly similarity with the second anomaly similarity to obtain a target anomaly similarity; When it is determined that the target normal similarity is less than the target abnormal similarity, it is determined that the ship diesel engine corresponding to the target image to be tested has a fault.

9. 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 according to any one of claims 1 to 4.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 4 are implemented.

Images