A centrifuge fault early warning method, device and equipment

Abstract

The application provides a centrifuge fault early warning method, device and equipment, and relates to the centrifuge field, which solves the problem that the centrifuge must be stopped during the working process. The centrifuge fault early warning method is characterized in that: the rotor system of the centrifuge is discretized, at least one component of the discretized rotor system is obtained, the rotor system motion equation is determined according to the at least one component, the rotor system motion equation is corrected, the centrifuge fault prediction model is determined through the corrected rotor system motion equation, the real-time parameters of the at least one component of the discretized rotor system of the centrifuge are input into the centrifuge fault prediction model for prediction, the fault prediction result including the offset degree of the at least one component of the discretized rotor system is obtained, and the functions of online monitoring, trend analysis and fault early warning of the centrifuge are realized, so that the preventive maintenance of the centrifuge is achieved.

Description

Technical Field

[0001] The present invention relates to the field of centrifuges, and in particular to a centrifuge fault warning method, device and equipment. Background Art

[0002] The decanter centrifuges (hereinafter referred to as "centrifuges") used in spent fuel reprocessing plants utilize the centrifugal force generated by the high-speed rotation of the rotor to separate the insoluble solid and liquid phases in the feed stream. They are an essential step in the reprocessing process, and therefore their stable operation is crucial. Traditional centrifuge maintenance typically relies on established inspection protocols based on past experience. Upon a malfunction, technicians conduct on-site troubleshooting, develop a maintenance plan, and then carry out repairs. This constitutes post-event inspection and maintenance. When a serious centrifuge malfunction causes downtime, multiple maintenance personnel must enter the radiation area to disassemble and inspect the centrifuge, making inspection and maintenance extremely difficult. The cost of a single disassembly and repair is enormous, increasing the risk of radiation exposure for maintenance personnel and causing plant downtime, resulting in significant economic losses. Even after reinstallation, the lifespan of the centrifuge equipment is significantly shortened, hindering process operation. Therefore, fault early warning of the mechanical status of key centrifuge components is essential. Fault early warning can effectively mitigate the phenomenon of centrifuge downtime caused by failures and guide process personnel in implementing preventive maintenance.

[0003] Currently, equipment failure early warning technology starts with two bearing failures at the feed end of a centrifugal dehydrator. After a detailed analysis of the causes of the failures, vibration monitoring technology was introduced to the centrifugal dehydrator. Through monitoring, the failure location of components and their failure development trends were determined, guiding inspection personnel to make maintenance decisions. However, according to actual operating conditions, although this method has certain guiding significance, there are many factors that affect the normal operation of the centrifuge, especially in high-noise and high-radiation environments. Vibration monitoring alone is not enough to accurately describe potential failures of key components. Summary of the Invention

[0004] The present invention provides a centrifuge fault warning method, device and equipment, which solve the problem that the centrifuge must be shut down due to a fault during operation.

[0005] In order to solve the above technical problems, the technical solutions of the present invention are as follows:

[0006] An embodiment of the present invention provides a centrifuge fault warning method, comprising:

[0007] determining a motion equation of the rotor system based on at least one component of a discretized rotor system of the centrifuge;

[0008] Determining a weak point and a maximum deformation of at least one component of the centrifuge;

[0009] Modifying the rotor system motion equation according to the weak link and the maximum deformation of the at least one component to obtain a modified rotor system motion equation;

[0010] Determining full-field characteristic information during centrifuge motion deviation according to the corrected rotor system motion equation;

[0011] Determining a centrifuge fault prediction model based on the full-field feature information;

[0012] The real-time parameters of at least one component of the discretized rotor system of the centrifuge are input into the centrifuge fault prediction model for prediction, and a fault prediction result including the offset degree of at least one component of the discretized rotor system is obtained and output.

[0013] Optionally, determining the motion equation of the rotor system based on at least one component of the discretized rotor system of the centrifuge includes:

[0014] At least one component of a discretized rotor system of a centrifuge Perform modal analysis to form the rotor system motion equation ;

[0015] Among them, M is the mass matrix of the centrifuge rotor system, C is the damping matrix of the centrifuge rotor system, K is the stiffness matrix of the centrifuge rotor system, X is the displacement vector of the discrete mass point of the centrifuge rotor system; F is the vector of the excitation force.

[0016] Optionally, determining a weak link and a maximum deformation of at least one component of the centrifuge includes:

[0017] The finite element model is optimized using the experimental modal analysis method to obtain the rotor system motion equation ;

[0018] right Solve the problem and perform rotor dynamic imbalance response analysis on the optimized finite element model to obtain the vibration characteristic parameters and response vibration modes of the centrifuge under normal working conditions and typical fault conditions, and determine at least one component of the centrifuge Weak links and the maximum deformation .

[0019] Optionally, the rotor system motion equation is modified according to the weak link and maximum deformation of the at least one component to obtain a modified rotor system motion equation, including:

[0020] According to at least one component Weak links and maximum deformation For initial analysis basis, simulate the loading and unloading process, and timely correct the rotor system motion equation , obtain the corrected rotor system motion equation .

[0021] Optionally, according to the corrected rotor system motion equation, determine the full-field feature information in the centrifuge motion offset process, including:

[0022] Perform rotor dynamic unbalance response analysis on the corrected finite element model to obtain at least one component of the centrifuge Stress weak link set { }, and maximum deformation variable set { };

[0023] Simulate the centrifuge rotor system under normal working condition and typical fault working condition to form a sensor information matrix set { }, wherein, is the amplitude of the centrifuge rotor in the simulation process, is the speed of the centrifuge rotor in the simulation process, is the temperature of the centrifuge rotor in the simulation process, is the phase sensor measurement information of the centrifuge rotor in the simulation process;

[0024] Take the initial position of the centrifuge mass point in the shutdown state as the benchmark to form the centrifuge motion offset trend trajectory diagram at the time, obtain the motion offset matrix set { }, wherein, is the amplitude set of the centrifuge rotor in the simulation process, is the speed set of the centrifuge rotor in the simulation process, is the temperature set of the centrifuge rotor in the simulation process, is the phase sensor measurement information set of the centrifuge rotor in the simulation process;

[0025] At the same time, analyze the measured data of the centrifuge in the post-processing plant to obtain the sensor information matrix set { } and the motion offset matrix set { }, wherein, is the amplitude of the centrifuge rotor in the centrifuge measurement process, is the speed of the centrifuge rotor in the centrifuge measurement process, is the temperature of the centrifuge rotor in the centrifuge measurement process, is the phase sensor measurement information of the centrifuge rotor in the centrifuge measurement process, is the amplitude set of the centrifuge rotor in the centrifuge measurement process, a set of rotation speeds of the centrifuge rotor during the centrifuge real-time measurement process, a set of temperatures of the centrifuge rotor during the centrifuge real-time measurement process, a set of phase sensor measurement information of the centrifuge rotor during the centrifuge real-time measurement process;

[0026] fusion processing of the amplitude, rotation speed, temperature, and phase sensor measurement information offsets in the set of motion offset matrices based on wavelet transform, to convert them into a time-frequency image, and obtain a time-frequency image set ;

[0027] fusion processing of the amplitude, rotation speed, temperature, and phase sensor measurement information offsets in the set of motion offset matrices based on wavelet transform, to convert them into a time-frequency image, and obtain a time-frequency image set ;

[0028] According to and , the full-field feature information during the centrifuge motion offset process is extracted.

[0029] Optionally, according to the full-field feature information, a centrifuge fault prediction model is determined, including:

[0030] The amplitude sensor values collected by the centrifuge monitoring system and the full-field feature information are used to train a preset neural network fault prediction model, and a centrifuge fault prediction model is obtained.

[0031] wherein the set of motion offset matrices and are input as model training samples, the time-frequency image set is defined as a training sample set, and the time-frequency image set is defined as a test sample set.

[0032] Optionally, real-time parameters of at least one component of the discretized rotor system of the centrifuge are input into the centrifuge fault prediction model for prediction, and a fault prediction result including the offset degree of the at least one component of the discretized rotor system is obtained, including:

[0033] The modal of the centrifuge to be detected is classified and recognized by using the topmost connection function in the neural network fault prediction model, and the running instability degree of at least one component of the discretized rotor system of the centrifuge to be detected is obtained.

[0034] The running instability degree is matched with the maximum deformation variable, and a fault prediction result including the offset degree of the at least one component of the discretized rotor system is obtained.

[0035] The embodiment of the present application also provides a centrifuge fault early warning device, comprising:

[0036] The acquisition module is used for determining a rotor system motion equation according to at least one component of a discretized rotor system of the centrifuge; determining a stress weak link and a maximum deformation of the at least one component of the centrifuge; correcting the rotor system motion equation according to the stress weak link and the maximum deformation of the at least one component to obtain a corrected rotor system motion equation; determining full-field characteristic information in a centrifuge motion excursion process according to the corrected rotor system motion equation; and determining a centrifuge fault prediction model according to the full-field characteristic information.

[0037] The processing module is used for inputting real-time parameters of the at least one component of the discretized rotor system of the centrifuge into the centrifuge fault prediction model for prediction to obtain a fault prediction result including a displacement degree of the at least one component of the discretized rotor system and outputting the fault prediction result.

[0038] The embodiment of the present application also provides a computing device, comprising a processor and a memory storing a computer program, wherein the computer program is executed by the processor to perform the centrifuge fault early warning method.

[0039] The embodiment of the present application also provides a computer readable storage medium storing instructions, wherein the instructions are executed on a computer to make the computer perform the centrifuge fault early warning method.

[0040] The above scheme of the present application has at least the following beneficial effects:

[0041] The above scheme of the present application has at least the following beneficial effects: BRIEF DESCRIPTION OF DRAWINGS

[0042] Figure 1 is a flowchart of the centrifuge fault early warning method of the present application;

[0043] Figure 2 is a module block diagram of the centrifuge fault early warning device of the present application. DETAILED DESCRIPTION

[0044] Exemplary embodiments of the present application will be described herein below with reference to the accompanying drawings. While exemplary embodiments of the present application are shown in the drawings, it is understood that the present application can be embodied in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the application to those skilled in the art.

[0045] As shown in Figure 1 An embodiment of the present application provides a centrifuge fault early warning method, comprising:

[0046] Step 11, determining a rotor system motion equation according to at least one component of a discretized rotor system of the centrifuge;

[0047] Step 12, determining a force-weak link and a maximum deformation of the at least one component of the centrifuge;

[0048] Step 13, correcting the rotor system motion equation according to the force-weak link and the maximum deformation of the at least one component, to obtain a corrected rotor system motion equation;

[0049] Step 14, determining full-field feature information in a centrifuge motion excursion process according to the corrected rotor system motion equation;

[0050] Step 15, determining a centrifuge fault prediction model according to the full-field feature information;

[0051] Step 16, inputting real-time parameters of the at least one component of the discretized rotor system of the centrifuge into the centrifuge fault prediction model for prediction, to obtain a fault prediction result including a displacement degree of the at least one component of the discretized rotor system, and outputting.

[0052] In the embodiment, the rotor system of the centrifuge is discretized to obtain at least one component of a discretized rotor system, a rotor system motion equation is determined according to the at least one component, the rotor system motion equation is corrected, a centrifuge fault prediction model is determined through the corrected rotor system motion equation, and finally real-time parameters of the at least one component of the discretized rotor system of the centrifuge are input into the centrifuge fault prediction model for prediction, to obtain a fault prediction result including a displacement degree of the at least one component of the discretized rotor system, so as to realize the functions of online monitoring, trend analysis and fault early warning of the centrifuge, achieve the purpose of preventive maintenance of the centrifuge, and solve the problem of machine stoppage due to faults in the working process of the existing centrifuge.

[0053] In an optional embodiment of the present application, step 11 can comprise:

[0054] At least one component of a discrete rotor system of a centrifuge Carrying out modal analysis to form a rotor system motion equation ;

[0055] Wherein, M is a mass matrix of the centrifuge rotor system, C is a damping matrix of the centrifuge rotor system, K is a stiffness matrix of the centrifuge rotor system, X is a displacement vector of discrete mass points of the centrifuge rotor system; F is a vector of excitation forces.

[0056] In the embodiment, the at least one component Comprise the balance plate, the drum, the liquid distribution disc and the sealing sleeve and the like components of the centrifuge;The excitation force F is divided into: the impact force caused by the non-uniformity of the material liquid (in the material loading and unloading process, the material liquid rotating speed and the centrifuge rotating speed are inconsistent, which will cause certain influence on the centrifuge, and under certain specific working conditions, it will exceed the centrifuge vibration alarm value, even the shutdown value), the excitation force caused by the abnormal work of part of mechanical structure (such as drum rupture, sealing sleeve rupture, bearing wear, screw loosening, coupling loosening, part machining precision, etc.).

[0057] In an optional embodiment of the application, step 12 can comprise:

[0058] Adopting the test modal analysis method to optimize the finite element model to obtain the rotor system motion equation ;

[0059] Solving , and carrying out rotor dynamic unbalance response analysis on the optimized finite element model to obtain the vibration characteristic parameters and response mode shapes of the centrifuge under normal working conditions and typical fault working conditions, and determining the at least one component of the centrifuge under stress weak link and the maximum deformation .

[0060] In the embodiment, the at least one component under stress weak link is determined by solving the equation (1), and the maximum deformation is determined by solving the equation (2). Wherein, X is a displacement vector of discrete mass points of the centrifuge rotor system, F is a vector of excitation forces, and . ; according to the equation characteristic root, the equation characteristic root can be obtained = ; wherein, is a system damping coefficient, Damped natural frequency Natural frequency of undamped system, Is a positive integer.

[0061] In an alternative embodiment of the application, step 13 can include:

[0062] According to at least one component Weak link of stress and maximum deformation For initial analysis, simulate the loading and unloading process, and timely correct the rotor system motion equation , get the corrected rotor system motion equation .

[0063] In a preferred embodiment, according to at least one component Weak link of stress and maximum deformation For initial analysis, simulate the loading and unloading process, and timely correct the rotor system motion equation , get the corrected rotor system motion equation .

[0064] In an alternative embodiment of the application, step 14 can include:

[0065] Step 141, the rotor dynamic unbalance response analysis is carried out to the corrected finite element model, at least one component Weak link of stress and maximum deformation } set, and maximum deformation } set of centrifuge is obtained;

[0066] Step 142, the centrifuge rotor system under normal working condition and typical fault working condition is simulated to form a sensor information matrix set }, wherein, The amplitude of the centrifuge rotor in the simulation process, The speed of the centrifuge rotor in the simulation process, The temperature of the centrifuge rotor in the simulation process, The phase sensor measurement information of the centrifuge rotor in the simulation process;

[0067] Step 143, taking the initial position of the centrifuge mass point in the shutdown state as the reference, forming The motion offset trend trajectory diagram of the centrifuge at time t, get the motion offset matrix set }, wherein, The amplitude of the centrifuge rotor in the simulation process, a set of amplitudes of the centrifuge rotor in the simulation process, a set of temperatures of the centrifuge rotor in the simulation process, a set of phase sensor measurement information of the centrifuge rotor in the simulation process;

[0068] Step 144, while analyzing the measured data of the centrifuge in the post-treatment plant, a set of sensor information matrices and a set of motion offset matrices are obtained, wherein, is the amplitude of the centrifuge rotor in the measured process of the centrifuge, is the rotational speed of the centrifuge rotor in the measured process of the centrifuge, is the temperature of the centrifuge rotor in the measured process of the centrifuge, is the phase sensor measurement information of the centrifuge rotor in the measured process of the centrifuge, is the amplitude set of the centrifuge rotor in the measured process of the centrifuge, is the rotational speed set of the centrifuge rotor in the measured process of the centrifuge, is the temperature set of the centrifuge rotor in the measured process of the centrifuge, is the set of phase sensor measurement information of the centrifuge rotor in the measured process of the centrifuge;

[0069] Step 145, based on the wavelet transform, the amplitude, rotational speed, temperature, and phase sensor measured information offset in the set of motion offset matrices are fused and converted into a time-frequency image to obtain a set of time-frequency images ;

[0070] Step 146, using wavelet transform, the amplitude, rotational speed, temperature, and phase sensor measured information offset in the set of motion offset matrices are fused and converted into a time-frequency image to obtain a set of time-frequency images ;

[0071] Step 147, according to and , the full-field feature information in the motion offset process of the centrifuge is extracted.

[0072] In an optional embodiment of the application, step 15 can include:

[0073] The amplitude sensor values collected by the centrifuge monitoring system and the full-field feature information are used to train a preset neural network fault prediction model to obtain a centrifuge fault prediction model;

[0074] wherein the set of motion offset matrices and A set of time-frequency images as model training sample input A set of time-frequency images is defined as a training sample set A test sample set is defined.

[0075] In the embodiment, when the preset neural network fault prediction model is trained, the network model parameters are updated in a way of random gradient descent and error back propagation, the loss value and the training accuracy of each iteration are observed, when the loss value remains stable and no longer continues to decrease, the early stopping method is used to terminate the training, the network structure and the optimal parameters obtained by updating are saved, and then the test sample set The trained neural network model is verified, if the verification result is not ideal, the model parameters are randomly initialized and the network structure is adjusted, the sample amount of the training set is increased, the model is retrained until the accuracy requirement is met, and the centrifuge fault prediction model is obtained.

[0076] In an optional embodiment of the present application, step 16 can include:

[0077] The mode of the centrifuge to be detected is classified and recognized by using the topmost layer connection function in the neural network fault prediction model, and the operation instability degree of at least one component of the discretized rotor system of the centrifuge to be detected is obtained.

[0078] The operation instability degree is matched with the maximum deformation variable to obtain a fault prediction result including the offset degree of at least one component of the discretized rotor system.

[0079] The centrifuge fault early warning method can be used for centrifuges with typical characteristics of vertical flexibility and long-term operation. The centrifuge fault early warning method obtains the operation instability degree of the centrifuge under various working conditions through the centrifuge fault prediction model, is used for identifying potential faults of the centrifuge, changes the existing post-maintenance mode of the centrifuge, realizes the functions of online monitoring, trend analysis and fault early warning of the centrifuge, achieves the purpose of preventive maintenance of the centrifuge, solves the problem of shutdown of the centrifuge during operation, provides a basis for judgment and handling of the fault decision of the operator, thereby improves the service life and reliability of the centrifuge equipment in a high-noise environment, ensures the operation rate of the production line, reduces the radiation dose of the inspection and maintenance personnel, has generalization ability, and plays a positive role in intelligent operation of post-processing and related field equipment.

[0080] As shown in Figure 2 The embodiment of the present application also provides a centrifuge fault early warning device 20, which comprises:

[0081] An acquisition module 21 is configured to determine a rotor system motion equation based on at least one component of a discretized rotor system of a centrifuge; determine a weak link and a maximum deformation of at least one component of the centrifuge; modify the rotor system motion equation based on the weak link and the maximum deformation of the at least one component to obtain a modified rotor system motion equation; determine full-domain feature information during centrifuge motion deviation based on the modified rotor system motion equation; and determine a centrifuge fault prediction model based on the full-domain feature information.

[0082] The processing module 22 is configured to input the real-time parameters of at least one component of the discretized rotor system of the centrifuge into the centrifuge fault prediction model for prediction, obtain a fault prediction result including the offset of at least one component of the discretized rotor system, and output the result.

[0083] Optionally, determining the rotor system motion equation based on at least one component of the discretized rotor system of the centrifuge includes:

[0084] At least one component of a discretized rotor system of a centrifuge Perform modal analysis to form the rotor system motion equation ;

[0085] Among them, M is the mass matrix of the centrifuge rotor system, C is the damping matrix of the centrifuge rotor system, K is the stiffness matrix of the centrifuge rotor system, X is the displacement vector of the discrete mass point of the centrifuge rotor system; F is the vector of the excitation force.

[0086] Optionally, determining a weak link and a maximum deformation of at least one component of the centrifuge includes:

[0087] The finite element model is optimized using the experimental modal analysis method to obtain the rotor system motion equation ;

[0088] right Solve the problem and perform rotor dynamic imbalance response analysis on the optimized finite element model to obtain the vibration characteristic parameters and response vibration modes of the centrifuge under normal working conditions and typical fault conditions, and determine at least one component of the centrifuge Weak links and the maximum deformation .

[0089] Optionally, the rotor system motion equation is modified according to the weak link and maximum deformation of the at least one component to obtain a modified rotor system motion equation, including:

[0090] According to at least one component Weak links and maximum deformation For initial analysis, simulate the loading and unloading process, and timely correct the rotor system motion equation , to obtain the corrected rotor system motion equation .

[0091] Optionally, according to the corrected rotor system motion equation, determine the full-field feature information in the centrifuge motion offset process, including:

[0092] Perform rotor dynamic unbalance response analysis on the corrected finite element model to obtain at least one component of the corrected centrifuge The stress weak link set { }, and the maximum deformation variable set { };

[0093] Simulate the centrifuge rotor system under normal working conditions and typical fault working conditions to form a sensor information matrix set { }, wherein, is the amplitude of the centrifuge rotor during simulation, is the speed of the centrifuge rotor during simulation, is the temperature of the centrifuge rotor during simulation, is the phase sensor measurement information of the centrifuge rotor during simulation;

[0094] Take the initial position of the centrifuge mass point in the shutdown state as the benchmark to form the centrifuge motion offset trend trajectory diagram at the time, to obtain a motion offset matrix set { }, wherein, is the amplitude set of the centrifuge rotor during simulation, is the speed set of the centrifuge rotor during simulation, is the temperature set of the centrifuge rotor during simulation, is the phase sensor measurement information set of the centrifuge rotor during simulation;

[0095] At the same time, analyze the measured data of the centrifuge in the post-processing plant to obtain the sensor information matrix set { } and the motion offset matrix set { }, wherein, is the amplitude of the centrifuge rotor during centrifuge measurement, is the speed of the centrifuge rotor during centrifuge measurement, is the temperature of the centrifuge rotor during centrifuge measurement, is the phase sensor measurement information of the centrifuge rotor during centrifuge measurement, A vibration amplitude set of a centrifuge rotor during a centrifuge real-time measurement process, A rotation speed set of a centrifuge rotor during a centrifuge real-time measurement process, A temperature set of a centrifuge rotor during a centrifuge real-time measurement process, A phase sensor measurement information set of a centrifuge rotor during a centrifuge real-time measurement process;

[0096] Fusion processing of vibration amplitude, rotation speed, temperature, and phase sensor measurement information offsets in the motion offset matrix set is performed based on wavelet transform, and the vibration amplitude, rotation speed, temperature, and phase sensor measurement information offsets are converted into time-frequency images to obtain a time-frequency image set ;

[0097] Fusion processing of vibration amplitude, rotation speed, temperature, and phase sensor measurement information offsets in the motion offset matrix set is performed using wavelet transform, and the vibration amplitude, rotation speed, temperature, and phase sensor measurement information offsets are converted into time-frequency images to obtain a time-frequency image set ;

[0098] According to and , full-field feature information during centrifuge motion offset is extracted.

[0099] Optionally, a centrifuge fault prediction model is determined according to the full-field feature information, including:

[0100] A preset neural network fault prediction model is trained using amplitude sensor values collected by a centrifuge monitoring system and the full-field feature information, and a centrifuge fault prediction model is obtained.

[0101] The motion offset matrix set and are input as model training samples, the time-frequency image set is defined as a training sample set, and the time-frequency image set is defined as a test sample set.

[0102] Optionally, real-time parameters of at least one component of a discretized rotor system of a centrifuge are input into the centrifuge fault prediction model for prediction to obtain a fault prediction result including an offset degree of the at least one component of the discretized rotor system, including:

[0103] A mode of a centrifuge to be detected is classified and recognized using a topmost layer connection function in the neural network fault prediction model, and an operation instability degree of at least one component of a discretized rotor system of the centrifuge to be detected is obtained.

[0104] The operation instability degree is matched with a maximum deformation variable to obtain a fault prediction result including an offset degree of the at least one component of the discretized rotor system.

[0105] It should be noted that the device corresponds to the fault early warning method of the centrifuge described above, and all the implementation manners in the above method are applicable to the embodiments of the device and can achieve the same technical effects.

[0106] The embodiments of the present application also provide a computing device, comprising a processor and a memory storing a computer program, when the computer program is run by the processor, the fault early warning method of the centrifuge described above is executed. All the implementation manners in the above method embodiments are applicable to the embodiments and can achieve the same technical effects.

[0107] The embodiments of the present application also provide a computer readable storage medium storing instructions, when the instructions are run on a computer, the computer executes the fault early warning method of the centrifuge described above. All the implementation manners in the above method embodiments are applicable to the embodiments and can achieve the same technical effects.

[0108] Those skilled in the art can understand that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are realized in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to realize the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0109] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described system, device and unit can refer to the corresponding processes in the foregoing method embodiments, which will not be repeated here.

[0110] In the embodiments provided by the present application, it should be understood that the disclosed device and method can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There can be another division manner in actual implementation. For example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed mutual couplings or direct couplings or communication connections between the units can be indirect couplings or communication connections through some interfaces, devices or units, and can be electrical, mechanical or in other forms.

[0111] The units described as separate components may or may not be physically separate, and the components displayed as units may or may not be physical units, i.e. may be located in one place, or may be distributed on multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment scheme.

[0112] In addition, each functional unit in each embodiment of the present application can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit.

[0113] If the functions are realized in the form of software functional units and sold or used as independent products, they can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application or the parts of the present application that essentially contribute to the prior art or the parts of the technical solutions can be embodied in the form of software products. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, ROM, RAM, magnetic disk or optical disk, and various program code storage media.

[0114] In addition, it should be noted that in the device and method of the present application, it is obvious that each component or each step can be decomposed and / or recombined. These decompositions and / or recombination should be considered as equivalent solutions of the present application. And the steps of executing the above series of processes can naturally be executed in time sequence according to the order of description, but it is not necessary to be executed in time sequence, and some steps can be executed in parallel or independently of each other. It can be understood by those skilled in the art that all or any steps or components of the method and device of the present application can be realized in hardware, firmware, software or their combination in any computing device (including processor, storage medium, etc.) or network of computing devices, which can be realized by those skilled in the art using their basic programming skills after reading the description of the present application.

[0115] Therefore, the object of the present application can also be achieved by running a program or a set of programs on any computing device. The computing device can be a commonly known general purpose device. Therefore, the object of the present application can also be achieved by merely providing a program product containing program code for implementing the method or device. That is, such a program product also constitutes the present application, and a storage medium storing such a program product also constitutes the present application. Obviously, the storage medium can be any commonly known storage medium or any storage medium developed in the future. It is also necessary to point out that in the device and method of the present application, obviously, the components or steps can be decomposed and / or recombined. These decompositions and / or recombinations should be considered as equivalent solutions of the present application. Moreover, the steps of performing the above series of processes can naturally be executed in time sequence according to the order of description, but do not necessarily have to be executed in time sequence. Some steps can be executed in parallel or independently of each other.

[0116] The above is the preferred embodiment of the present application, and it should be pointed out that for those skilled in the art, several improvements and refinements can be made without departing from the principles of the present application, and these improvements and refinements should also be considered as the protection scope of the present application.

Claims

1. A centrifuge fault early warning method, comprising: determining a rotor system motion equation according to at least one component of a discretized rotor system of a centrifuge; determining a stress weak link and a maximum deformation of the at least one component of the centrifuge; correcting the rotor system motion equation according to the stress weak link and the maximum deformation of the at least one component to obtain a corrected rotor system motion equation; determining full-field characteristic information in a centrifuge motion excursion process according to the corrected rotor system motion equation; determining a centrifuge fault prediction model according to the full-field characteristic information; inputting real-time parameters of the at least one component of the discretized rotor system of the centrifuge into the centrifuge fault prediction model for prediction to obtain a fault prediction result including an excursion degree of the at least one component of the discretized rotor system, and outputting; wherein the rotor system motion equation is determined according to at least one component of a discretized rotor system of a centrifuge, comprising: Discretization of at least one component of a rotor system of a centrifuge Performing modal analysis, forming rotor system motion equation ; wherein M is a mass matrix of the centrifuge rotor system, C is a damping matrix of the centrifuge rotor system, K is a stiffness matrix of the centrifuge rotor system, and X is a displacement vector of a discretized mass point of the centrifuge rotor system; F is a vector of excitation force; wherein the stress weak link and the maximum deformation of the at least one component of the centrifuge are determined, comprising: The test modal analysis method is used to optimize the finite element model to obtain a rotor system motion equation ; To solving, and the optimized finite element model is analyzed for rotor dynamic unbalance response, to obtain the normal working condition and typical fault working condition under centrifuge each order vibration characteristic parameter and response mode, to determine at least one component weak link and the maximum deformation ; wherein the rotor system motion equation is corrected according to the stress weak link and the maximum deformation of the at least one component to obtain a corrected rotor system motion equation, comprising: According to at least one component Stress weak link and maximum deformation For initial analysis, simulate the loading and unloading process, and timely correct the rotor system motion equation , get the corrected rotor system motion equation ; wherein the full-field characteristic information in the centrifuge motion excursion process is determined according to the corrected rotor system motion equation, comprising: performing a rotor dynamic unbalance response analysis on the modified finite element model to obtain at least one component of the modified centrifuge a set of weak force links } and a set of maximum deformation values } Simulate the centrifuge rotor system under normal working condition and typical fault working condition to form a sensor information matrix set } wherein, is the amplitude of the centrifuge rotor in the simulation process, is the speed of the centrifuge rotor in the simulation process, is the temperature of the centrifuge rotor in the simulation process, is the phase sensor measurement information of the centrifuge rotor in the simulation process; Taking the initial position of the centrifuge mass point in the shutdown state as the reference, the The centrifuge motion deviation trend trajectory diagram at each moment, and the motion deviation matrix set { },in, is the amplitude set of the centrifuge rotor during the simulation process, is the speed set of the centrifuge rotor during the simulation process, is the temperature set of the centrifuge rotor during the simulation process, It is a collection of phase sensor measurement information of the centrifuge rotor during the simulation process; At the same time, the measured data of the centrifuge in the post-processing plant are analyzed to obtain the sensor information matrix set { } and the motion offset matrix set { },in, is the amplitude of the centrifuge rotor during the actual measurement process, is the speed of the centrifuge rotor during the actual measurement process, is the temperature of the centrifuge rotor during the actual measurement process, The phase sensor measurement information of the centrifuge rotor during the centrifuge measurement process is is the amplitude set of the centrifuge rotor during the centrifuge measurement process, is the speed set of the centrifuge rotor during the centrifuge measurement process, is the temperature set of the centrifuge rotor during the centrifuge measurement process, It is a collection of measurement information of the phase sensor of the centrifuge rotor during the actual measurement of the centrifuge; Based on the wavelet transform to the motion offset matrix set } in the amplitude, the speed, the temperature, the phase sensor measured information offset fusion processing, it is converted into time-frequency image, obtains time-frequency image set ; Using wavelet transform to fuse the motion offset matrix set of field sensors } and convert the information offset of amplitude, rotating speed, temperature and phase sensor into time-frequency image to obtain time-frequency image set ; according to and , extract the full-field feature information during the centrifuge motion offset process.

2. The failure warning method of a centrifuge according to claim 1, characterized by, the centrifuge fault prediction model is determined according to the full-field characteristic information, comprising: a preset neural network fault prediction model is trained using amplitude sensor values collected by a centrifuge monitoring system and the full-field characteristic information to obtain the centrifuge fault prediction model; wherein the set of motion offset matrices and as model training sample input, the set of time-frequency images defined as the set of training samples, the set of time-frequency images defined as the set of test samples.

3. The centrifuge failure early warning method of claim 1, wherein, the real-time parameters of the at least one component of the discretized rotor system of the centrifuge are inputted into the centrifuge fault prediction model for prediction to obtain a fault prediction result including an excursion degree of the at least one component of the discretized rotor system, comprising: the mode of the centrifuge to be detected is classified and recognized using a topmost layer connection function in the neural network fault prediction model to obtain an operation instability degree of the at least one component of the discretized rotor system of the centrifuge to be detected; the operation instability degree is matched with the maximum deformation to obtain a fault prediction result including an excursion degree of the at least one component of the discretized rotor system.

4. A failure warning device for a centrifuge, characterized by comprising: comprising: an acquisition module for determining a rotor system motion equation according to at least one component of a discretized rotor system of a centrifuge; determining a stress weak link and a maximum deformation of the at least one component of the centrifuge; correcting the rotor system motion equation according to the stress weak link and the maximum deformation of the at least one component to obtain a corrected rotor system motion equation; determining full-field characteristic information in a centrifuge motion excursion process according to the corrected rotor system motion equation; determining a centrifuge fault prediction model according to the full-field characteristic information; The processing module is configured to input real-time parameters of at least one component of a discretized rotor system of the centrifuge into the centrifuge fault prediction model for prediction, obtain a fault prediction result including a deviation degree of the at least one component of the discretized rotor system, and output the fault prediction result. The rotor system motion equation is determined according to at least one component of the discretized rotor system of the centrifuge, and includes: Discretizing at least one component of a rotor system of a centrifuge Performing modal analysis to form rotor system motion equations ; wherein M is a mass matrix of the rotor system of the centrifuge, C is a damping matrix of the rotor system of the centrifuge, K is a stiffness matrix of the rotor system of the centrifuge, and X is a displacement vector of a discretized mass point of the rotor system of the centrifuge; and F is a vector of excitation forces. The weak force link and the maximum deformation of the at least one component of the centrifuge are determined, and include: The test modal analysis method is used to optimize the finite element model to obtain a rotor system motion equation ; To solving, and the optimized finite element model is analyzed for rotor dynamic unbalance response, to obtain the normal working condition and the typical fault working condition under centrifuge each order vibration characteristic parameter and response mode, to determine at least one component weak link and the maximum deformation ; The rotor system motion equation is corrected according to the weak force link and the maximum deformation of the at least one component, and a corrected rotor system motion equation is obtained, including: According to at least one component Stress weak link and maximum deformation For initial analysis, simulate the loading and unloading process, and timely correct the rotor system motion equation , get the corrected rotor system motion equation ; The full-field characteristic information in the motion deviation process of the centrifuge is determined according to the corrected rotor system motion equation, including: performing a rotor dynamic unbalance response analysis on the modified finite element model to obtain at least one component of the modified centrifuge a set of weak force links , and a set of maximum deformation values ​ Simulate the centrifuge rotor system under normal working condition and typical fault working condition to form a sensor information matrix set } wherein, is the amplitude of the centrifuge rotor in the simulation process, is the speed of the centrifuge rotor in the simulation process, is the temperature of the centrifuge rotor in the simulation process, is the phase sensor measurement information of the centrifuge rotor in the simulation process; Taking the initial position of the centrifuge mass point in the shutdown state as the reference, the The centrifuge motion deviation trend trajectory diagram at each moment, and the motion deviation matrix set { },in, is the amplitude set of the centrifuge rotor during the simulation process, is the speed set of the centrifuge rotor during the simulation process, is the temperature set of the centrifuge rotor during the simulation process, It is a collection of phase sensor measurement information of the centrifuge rotor during the simulation process; At the same time, the measured data of the centrifuge of the post-processing plant are analyzed to obtain a sensor information matrix set } and a motion offset matrix set }, wherein, is an amplitude of the centrifuge rotor in the centrifuge measurement process, is a rotating speed of the centrifuge rotor in the centrifuge measurement process, is a temperature of the centrifuge rotor in the centrifuge measurement process, is phase sensor measurement information of the centrifuge rotor in the centrifuge measurement process, is an amplitude set of the centrifuge rotor in the centrifuge measurement process, is a rotating speed set of the centrifuge rotor in the centrifuge measurement process, is a temperature set of the centrifuge rotor in the centrifuge measurement process, is a phase sensor measurement information set of the centrifuge rotor in the centrifuge measurement process; based on wavelet transform to the motion offset matrix set The amplitude, rotational speed, temperature, and phase sensor measured information offset is fused and processed to convert into a time-frequency image to obtain a time-frequency image set ; Using wavelet transform to process the motion offset matrix set of field sensors } The amplitude, rotation speed, temperature and phase sensor measured information offset is fused and converted into time-frequency image to obtain a time-frequency image set ; According to and , the full-field feature information in the motion offset process of the extraction centrifuge is extracted.

5. A computing device, comprising: The full-field characteristic information in the motion deviation process of the centrifuge is determined according to the corrected rotor system motion equation, including: The processor and the memory storing a computer program, the computer program being executed by the processor to perform the method of any one of claims 1 to 3.

6. A computer-readable storage medium, characterized in that, The storage instruction, when executed on the computer, causes the computer to perform the method of any one of claims 1 to 3.

Images