Vibration trend-based auxiliary machine residual life prediction method and system
By setting vibration sensing points on power plant auxiliary equipment and constructing degradation simulation and evaluation models, early identification of equipment performance degradation and accurate life prediction are achieved, solving the problems of insufficient prediction accuracy and foresight in existing technologies, and improving equipment operation and maintenance efficiency and safety.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- JINING HUAYUAN HEAT POWER CO LTD
- Filing Date
- 2025-11-20
- Publication Date
- 2026-04-28
AI Technical Summary
Existing technologies cannot achieve early identification of the performance degradation process of power plant auxiliary equipment and accurate prediction of its remaining life, and the prediction accuracy and foresight based on statistical or simple time series models are limited.
By setting multiple vibration sensing points on power plant auxiliary equipment, vibration signals are collected to construct a degradation simulation model. Combined with the degradation assessment model, a linkage analysis is performed to generate the expected remaining life. The prediction results are then periodically corrected to improve prediction accuracy and early warning efficiency.
It enables accurate prediction of the service life of power plant auxiliary equipment, improves the accuracy of prediction and the efficiency of early warning of deterioration risks, and ensures the safe operation of equipment.
Smart Images
Figure CN121936096A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of power plant auxiliary equipment technology, and in particular to a method and system for predicting the remaining life of auxiliary equipment based on vibration trends. Background Technology
[0002] Rotating machinery auxiliary equipment, such as pumps, fans, and compressors, are key equipment in modern industrial production systems, and their operating status directly affects the safety, stability, and efficiency of the entire system. Therefore, accurately predicting their remaining service life and implementing predictive maintenance is of great significance for avoiding sudden downtime, reducing maintenance costs, and preventing catastrophic accidents.
[0003] Currently, the industry commonly uses vibration alarm methods based on fixed thresholds for auxiliary equipment condition monitoring and lifespan prediction. While this method can respond to sudden failures, it is essentially a reactive or ongoing maintenance approach and cannot achieve early identification of equipment performance degradation or advance prediction of remaining lifespan. Furthermore, some prediction methods based on statistics or simple time series models are insufficient in capturing the nonlinear, gradual performance changes caused by wear, fatigue, and other factors during long-term equipment operation, resulting in limited prediction accuracy and foresight. Summary of the Invention
[0004] The purpose of this application is to provide a method and system for predicting the remaining service life of auxiliary equipment based on vibration trends in order to solve the above-mentioned technical problems, thereby improving the accuracy of predicting the service life of auxiliary equipment in power plants and providing data support for the operation and maintenance of power plant equipment.
[0005] In some embodiments of this application, multiple vibration sensing points are selected based on the structural parameters of the power plant auxiliary equipment. By collecting the original vibration signals of each vibration sensing point, a corresponding degradation simulation model is constructed to predict the degradation state of each vibration sensing point, thereby achieving accurate prediction of the service life of the power plant auxiliary equipment and providing data support for the operation and maintenance of power plant equipment.
[0006] In some embodiments of this application, a degradation assessment model is constructed to perform a linkage analysis on the expected degradation state of all vibration sensing points, thereby improving the accuracy of the prediction of the remaining life of power plant auxiliary equipment. Furthermore, by periodically collecting vibration signals from each vibration sensing point, the prediction results are rolled over and corrected, thereby improving the early warning and maintenance efficiency of power plant auxiliary equipment degradation risks and ensuring the safe operation of power plant auxiliary equipment.
[0007] In some embodiments of this application, a method for predicting the remaining life of auxiliary equipment based on vibration trends is provided, including:
[0008] Multiple vibration sensing points are set according to the structural parameters of the power plant auxiliary equipment;
[0009] The initial vibration packets of each vibration sensing point are obtained, and the expected remaining life of the power plant auxiliary equipment is generated based on all the initial vibration packets and the preset life prediction model.
[0010] The feedback vibration packets of each vibration sensing point are obtained according to the preset monitoring time nodes, and the expected remaining life is determined based on all monitoring data.
[0011] In some embodiments of this application, a preset lifetime prediction model is included, including:
[0012] Establish a sequence A of vibration sensing points, A = (a1, a2, ..., a...). i …a n ), where a i Let be the i-th vibration sensing point; n is the number of vibration sensing points.
[0013] The original vibration database is constructed based on all vibration sensing points;
[0014] Based on the vibration sensing point sequence A, a is set sequentially. i For target perception point;
[0015] First-level correlation data of target sensing points are generated based on the original vibration database;
[0016] A degradation simulation model of the target sensing points is constructed based on the primary correlation data;
[0017] Deterioration simulation models for each vibration sensing point are generated sequentially.
[0018] A degradation assessment model is constructed based on all degradation simulation models and the original vibration database;
[0019] A lifetime prediction model is generated based on all degradation simulation models and degradation assessment models.
[0020] In some embodiments of this application, a degradation assessment model is constructed, including:
[0021] Based on the vibration sensing point sequence A, a is set sequentially. i For target perception point;
[0022] Multiple degradation sub-states of the target sensing point are generated based on the degradation simulation model of the target sensing point;
[0023] Multiple degraded sub-states are generated sequentially for each vibration sensing point;
[0024] Multiple evaluation scenarios are constructed based on all degraded sub-states;
[0025] Establish an evaluation scenario sequence B, B = (b1, b2, ..., bb) i …b m ), where b i Let m be the i-th evaluation scenario; m is the number of evaluation scenarios.
[0026] b is set sequentially according to the evaluation scenario sequence B. i Target assessment scenario;
[0027] A secondary association package for the target evaluation scenario is generated based on the original vibration database;
[0028] Based on the secondary association package, generate evaluation sub-strategies for the target evaluation scenario;
[0029] The evaluation sub-strategies for each evaluation scenario are generated sequentially, and a degradation evaluation model is generated based on all the evaluation sub-strategies.
[0030] In some embodiments of this application, generating the expected remaining lifespan of power plant auxiliary equipment includes:
[0031] Based on the vibration sensing point sequence A, a is set sequentially. i The sensing point to be evaluated;
[0032] The degradation simulation model of the sensing point to be evaluated is set as the target health model;
[0033] Obtain the initial vibration packet of the sensing point to be evaluated;
[0034] Generate the expected degradation curve of the sensing point to be evaluated based on the initial vibration package and the target health model;
[0035] The expected degradation curves for each vibration point are generated sequentially.
[0036] Establish multiple operating cycles;
[0037] Establish a periodic sequence T, T = (t1, t2, ..., tt3). i …t r ), where t i Let r be the i-th running cycle; r is the number of running cycles.
[0038] Risk assessment values for each operating cycle are generated sequentially based on the degradation assessment model.
[0039] The expected remaining lifespan of power plant auxiliary equipment is generated based on all risk assessment values.
[0040] In some embodiments of this application, the expected remaining lifespan of power plant auxiliary equipment is generated based on all risk assessment values, including:
[0041] t is set sequentially according to the operating cycle sequence T. i The target operating cycle;
[0042] Generate a first-level degradation feature package for the target operating cycle based on all expected degradation curves;
[0043] A first-level assessment strategy is generated based on the first-level degradation feature package and degradation assessment model;
[0044] Generate the risk assessment value f for the target operating cycle;
[0045]
[0046] Where n is the number of vibration sensing points; η i The influence factor for the i-th vibration sensing point is set according to the primary evaluation strategy; c i It is the degradation risk value of the i-th vibration sensing point within the target operating cycle, generated based on the expected degradation curve;
[0047] The first risk assessment threshold F1 is preset;
[0048] If f > F1, set the target operating cycle as the risk cycle, and generate the expected remaining lifespan based on the risk cycle;
[0049] If f < F1, generate the evaluation instruction for the next running cycle.
[0050] In some embodiments of this application, determining whether to modify the expected remaining lifetime includes:
[0051] Set the end time of each running cycle as the monitoring time node;
[0052] Obtain the feedback vibration packets of each vibration sensing point at the current monitoring time node;
[0053] The actual degradation curves of each vibration sensing point are generated based on all vibration feedback packets.
[0054] Generate the degradation deviation value for each vibration sensing point based on all actual degradation curves;
[0055] A corrected evaluation value d is generated based on all deterioration deviation values;
[0056] Preset correction evaluation value threshold D1;
[0057] If d > D1, generate a first-level correction instruction.
[0058] In some embodiments of this application, generating the corrected evaluation value d includes:
[0059] Construct a secondary degradation feature package based on all actual degradation curves;
[0060] A secondary assessment strategy is generated based on the degradation assessment model and the secondary degradation feature package;
[0061] Generate a corrected evaluation value d;
[0062]
[0063] Where g is the correction compensation coefficient; n is the number of vibration sensing points; η 2i The influence factor for the i-th vibration sensing point is set according to the secondary evaluation strategy; s i θ1 is the degradation deviation value of the i-th vibration sensing point; U1 is the preset first conversion coefficient; θ1 is the number of auxiliary evaluation indicators; β i Let j be the influence factor of the i-th auxiliary evaluation index; i It is the reference value of the i-th auxiliary evaluation index generated based on all deterioration deviation values.
[0064] Some embodiments of this application also include:
[0065] Generate the risk assessment value f1 for the current monitoring time point based on all actual degradation curves;
[0066]
[0067] Where n is the number of vibration sensing points; η 2i The influence factor for the i-th vibration sensing point is set according to the secondary evaluation strategy; c 2i It is the degradation risk value of the i-th vibration sensing point at the current monitoring time node, generated based on the actual degradation curve;
[0068] A second risk assessment threshold F2 is preset, and F2 < F1;
[0069] If f1 > F2, a Level 1 early warning instruction is generated at the current monitoring time point.
[0070] In some embodiments of this application, an auxiliary machine remaining life prediction system based on vibration trends is provided, including:
[0071] The central control unit is used to set multiple vibration sensing points according to the structural parameters of the power plant's auxiliary equipment;
[0072] The monitoring unit includes multiple monitoring sub-modules, which are located at various vibration sensing points;
[0073] The monitoring unit is used to collect vibration signals from each vibration sensing point.
[0074] The central control unit includes:
[0075] The first processing module is used to build a lifetime prediction model;
[0076] The second processing module is used to acquire the initial vibration packets of each vibration sensing point and generate the expected remaining life of the power plant auxiliary equipment based on all the initial vibration packets and the preset life prediction model.
[0077] The correction module is used to obtain feedback vibration packets from each vibration sensing point according to a preset monitoring time node, and to determine whether to correct the expected remaining lifespan based on all monitoring data.
[0078] The first processing module is also used for:
[0079] Establish a sequence A of vibration sensing points, A = (a1, a2, ..., a...). i …a n ), where a i Let be the i-th vibration sensing point; n is the number of vibration sensing points.
[0080] The original vibration database is constructed based on all vibration sensing points;
[0081] Based on the vibration sensing point sequence A, a is set sequentially. i For target perception point;
[0082] First-level correlation data of target sensing points are generated based on the original vibration database;
[0083] A degradation simulation model of the target sensing points is constructed based on the primary correlation data;
[0084] Deterioration simulation models for each vibration sensing point are generated sequentially.
[0085] A degradation assessment model is constructed based on all degradation simulation models and the original vibration database;
[0086] A lifetime prediction model is generated based on all degradation simulation models and degradation assessment models.
[0087] In some embodiments of this application, the second processing module is further configured to:
[0088] Based on the vibration sensing point sequence A, a is set sequentially. i The sensing point to be evaluated;
[0089] The degradation simulation model of the sensing point to be evaluated is set as the target health model;
[0090] Obtain the initial vibration packet of the sensing point to be evaluated;
[0091] Generate the expected degradation curve of the sensing point to be evaluated based on the initial vibration package and the target health model;
[0092] The expected degradation curves for each vibration point are generated sequentially.
[0093] Establish multiple operating cycles;
[0094] Establish a periodic sequence T, T = (t1, t2, ..., tt3). i …t r ), where t iLet r be the i-th running cycle; r is the number of running cycles.
[0095] Risk assessment values for each operating cycle are generated sequentially based on the degradation assessment model.
[0096] The expected remaining lifespan of power plant auxiliary equipment is generated based on all risk assessment values.
[0097] Compared with the prior art, the beneficial effects of the auxiliary machine remaining life prediction method and system based on vibration trend in this application are as follows:
[0098] Based on the structural parameters of power plant auxiliary equipment, multiple vibration sensing points are selected. By collecting the original vibration signals of each vibration sensing point, a corresponding degradation simulation model is constructed to predict the degradation state of each vibration sensing point, thereby achieving accurate prediction of the service life of power plant auxiliary equipment and providing data support for power plant equipment operation and maintenance.
[0099] By constructing a degradation assessment model, the expected degradation status of all vibration sensing points is analyzed in a coordinated manner, which improves the accuracy of the prediction of the remaining life of power plant auxiliary equipment. Furthermore, by periodically collecting vibration signals from each vibration sensing point, the prediction results are continuously corrected, thereby improving the early warning and maintenance efficiency of power plant auxiliary equipment degradation risks and ensuring the safe operation of power plant auxiliary equipment. Attached Figure Description
[0100] Figure 1 This is a flowchart illustrating a preferred embodiment of the present application of a method for predicting the remaining life of auxiliary equipment based on vibration trends. Detailed Implementation
[0101] The specific embodiments of this application will be described in further detail below with reference to the accompanying drawings and examples. The following examples are used to illustrate this application, but are not intended to limit the scope of this application.
[0102] In the description of this application, it should be understood that the terms "center", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this application.
[0103] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this application, unless otherwise stated, "a plurality of" means two or more.
[0104] In the description of this application, it should be noted that, unless otherwise expressly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection between two components. Those skilled in the art can understand the specific meaning of the above terms in this application based on the specific circumstances.
[0105] like Figure 1 As shown, a preferred embodiment of this application provides a method for predicting the remaining life of auxiliary equipment based on vibration trends, comprising:
[0106] S101: Multiple vibration sensing points are set according to the structural parameters of the power plant auxiliary equipment;
[0107] S102: Obtain the initial vibration packets of each vibration sensing point, and generate the expected remaining life of the power plant auxiliary equipment based on all the initial vibration packets and the preset life prediction model.
[0108] S103: Obtain feedback vibration packets from each vibration sensing point according to the preset monitoring time nodes, and determine whether to correct the expected remaining lifespan based on all monitoring data.
[0109] Specifically, by analyzing the equipment structure of power plant auxiliary equipment (such as fans, water pumps, coal mills, circulating water pumps, etc.), several key parts (such as bearing housings, non-drive ends of motors, etc., structural points that can generate vibration signals and reflect the health status of power plant auxiliary equipment) are selected. Vibration sensing points are set according to all key parts, where each vibration sensing point represents a key part.
[0110] Specifically, a monitoring submodule is set up at each vibration sensing point, and the monitoring submodule is preferably a vibration sensor. The vibration signal of each vibration sensing point is collected in real time by setting up the monitoring submodule.
[0111] It is understood that in the above embodiments, multiple vibration sensing points are selected based on the structural parameters of the power plant auxiliary equipment, and the corresponding degradation simulation model is constructed by collecting the original vibration signals of each vibration sensing point. This enables the prediction of the degradation state of each vibration sensing point, thereby achieving accurate prediction of the service life of the power plant auxiliary equipment and providing data support for the operation and maintenance of power plant equipment.
[0112] In a preferred embodiment of this application, the preset lifetime prediction model includes:
[0113] Establish a sequence A of vibration sensing points, A = (a1, a2, ..., a...). i …a n ), where a i Let be the i-th vibration sensing point; n is the number of vibration sensing points.
[0114] The original vibration database is constructed based on all vibration sensing points;
[0115] Based on the vibration sensing point sequence A, a is set sequentially. i For target perception point;
[0116] First-level correlation data of target sensing points are generated based on the original vibration database;
[0117] A degradation simulation model of the target sensing points is constructed based on the primary correlation data;
[0118] Deterioration simulation models for each vibration sensing point are generated sequentially.
[0119] A degradation assessment model is constructed based on all degradation simulation models and the original vibration database;
[0120] A lifetime prediction model is generated based on all degradation simulation models and degradation assessment models.
[0121] Specifically, the original vibration database includes vibration record data from each vibration sensing point (i.e., the continuous vibration signals and trends of each vibration signal at each vibration sensing point as the cumulative operating time increases at the current sensing point in the power plant auxiliary equipment; the data in the original vibration database can be generated after filtering based on historical vibration monitoring data and degradation test data).
[0122] Specifically, the primary correlation data refers to the vibration records of the target sensing points in the original vibration database. Analysis of this primary correlation data generates multiple vibration characteristic indicators, including but not limited to: root mean square value, peak value, kurtosis, skewness, waveform factor, impulse factor, amplitude of characteristic frequencies (such as bearing passage frequency and gear meshing frequency), sideband energy, and spectral centroid—all time-domain, frequency-domain, and time-frequency-domain characteristics that characterize the equipment's degradation state. Quantification of each vibration characteristic indicator ensures that its reference values fall within the same range. Furthermore, the better the real-time parameters of each vibration indicator represent the operating status of the power plant's auxiliary equipment, the higher the corresponding reference value.
[0123] Specifically, by analyzing the primary correlation data, sub-curves of how each vibration characteristic changes over time are generated, and all sub-curves are fitted to construct the anchoring degradation curve of the target sensing point. The anchoring degradation curve is then set as the degradation simulation model of the target vibration point.
[0124] Specifically, constructing a degradation assessment model includes:
[0125] Based on the vibration sensing point sequence A, a is set sequentially. i For target perception point;
[0126] Multiple degradation sub-states of the target sensing point are generated based on the degradation simulation model of the target sensing point;
[0127] Multiple degraded sub-states are generated sequentially for each vibration sensing point;
[0128] Multiple evaluation scenarios are constructed based on all degraded sub-states;
[0129] Establish an evaluation scenario sequence B, B = (b1, b2, ..., bb) i …b m ), where b i Let m be the i-th evaluation scenario; m is the number of evaluation scenarios.
[0130] b is set sequentially according to the evaluation scenario sequence B. i Target assessment scenario;
[0131] A secondary association package for the target evaluation scenario is generated based on the original vibration database;
[0132] Based on the secondary association package, generate evaluation sub-strategies for the target evaluation scenario;
[0133] The evaluation sub-strategies for each evaluation scenario are generated sequentially, and a degradation evaluation model is generated based on all the evaluation sub-strategies.
[0134] Specifically, based on the anchored degradation curve constructed from the target sensing point, the degradation percentage of the target sensing point is divided to generate multiple degradation percentage intervals (using a uniform division method, with the same span of degradation percentage within each interval, and the segmentation span can be set according to historical parameters), thereby generating multiple degradation sub-states, where each degradation sub-state corresponds to a different degradation percentage interval.
[0135] Specifically, multiple evaluation scenarios are constructed based on random combinations of the degradation sub-states of each vibration sensing point. In any two evaluation scenarios, the degradation percentages corresponding to each vibration sensing point are not exactly the same.
[0136] Specifically, the secondary correlation package includes the operating parameters of power plant auxiliary equipment under the conditions corresponding to the target assessment scenario (i.e., when each vibration sensing point is at its corresponding percentage of deterioration). By analyzing the data in the secondary correlation package, the risk probability (i.e., the probability of operational failure at each vibration sensing point) of each vibration sensing point in the target assessment model is generated. Based on the risk probability, a corresponding assessment impact factor is set; the higher the risk probability, the larger the reference value of the corresponding assessment impact factor. The mapping relationship between the two can be set based on historical parameters. An assessment sub-strategy for the target assessment scenario is constructed based on all assessment impact factors.
[0137] It is understandable that in the above embodiments, by constructing a degradation assessment model, the expected degradation state of all vibration sensing points is analyzed in a coordinated manner, thereby improving the accuracy of the prediction of the remaining life of power plant auxiliary equipment.
[0138] In a preferred embodiment of this application, generating the expected remaining lifespan of power plant auxiliary equipment includes:
[0139] Based on the vibration sensing point sequence A, a is set sequentially. i The sensing point to be evaluated;
[0140] The degradation simulation model of the sensing point to be evaluated is set as the target health model;
[0141] Obtain the initial vibration packet of the sensing point to be evaluated;
[0142] Generate the expected degradation curve of the sensing point to be evaluated based on the initial vibration package and the target health model;
[0143] The expected degradation curves for each vibration point are generated sequentially.
[0144] Establish multiple operating cycles;
[0145] Establish a periodic sequence T, T = (t1, t2, ..., tt3). i …t r ), where t i Let r be the i-th running cycle; r is the number of running cycles.
[0146] Risk assessment values for each operating cycle are generated sequentially based on the degradation assessment model.
[0147] The expected remaining lifespan of power plant auxiliary equipment is generated based on all risk assessment values.
[0148] Specifically, the system generates real-time parameter values for each vibration index at the current vibration sensing point based on the initial vibration packet of the current vibration sensing point. Based on the real-time parameter values of all vibration indices and the target health model, it determines the node position of the current vibration sensing point in the anchoring degradation curve and sets the remaining anchoring degradation curve after the node position as the expected degradation curve of the current vibration sensing point.
[0149] Specifically, the duration of the operating cycle can be set according to the probability of fluctuations in the operation of the power plant's auxiliary equipment. The greater the probability of fluctuations, the shorter the corresponding operating cycle. The mapping relationship between the two can be set based on historical parameters.
[0150] Specifically, the expected remaining lifespan of power plant auxiliary equipment is generated based on all risk assessment values, including:
[0151] t is set sequentially according to the operating cycle sequence T. i The target operating cycle;
[0152] Generate a first-level degradation feature package for the target operating cycle based on all expected degradation curves;
[0153] A first-level assessment strategy is generated based on the first-level degradation feature package and degradation assessment model;
[0154] Generate the risk assessment value f for the target operating cycle;
[0155]
[0156] Where n is the number of vibration sensing points; η i The influence factor for the i-th vibration sensing point is set according to the primary evaluation strategy; c i It is the degradation risk value of the i-th vibration sensing point within the target operating cycle, generated based on the expected degradation curve;
[0157] The first risk assessment threshold F1 is preset;
[0158] If f > F1, set the target operating cycle as the risk cycle, and generate the expected remaining lifespan based on the risk cycle;
[0159] If f < F1, generate the evaluation instruction for the next running cycle.
[0160] Specifically, based on the first-level degradation feature package, the degradation sub-state of each vibration sensing point is determined, and the corresponding evaluation sub-strategy for the evaluation scenario is selected as the first-level evaluation strategy.
[0161] Specifically, the set influence factor is the evaluation influence factor of each vibration sensing point in the first-level evaluation strategy.
[0162] Specifically, the degradation risk value can be set based on the sum of the differences between the expected values of various vibration indicators at the vibration sensing point within the current operating cycle (i.e., the reference values generated based on the expected degradation curve) and the optimal reference values (i.e., the reference values when the power plant auxiliary equipment is in its optimal operating state). The larger the sum of these differences, the greater the corresponding degradation risk value. The mapping relationship between the two can be set based on historical parameters.
[0163] Specifically, the first risk assessment threshold can be set based on historical parameters. When the real-time risk assessment value exceeds the preset first risk assessment threshold, it indicates that the power plant auxiliary equipment is at risk of being scrapped, i.e., it is at a point in its remaining lifespan. The end time of this operating cycle is set as the target lifespan point. The remaining lifespan of the power plant auxiliary equipment is generated by calculating the time difference between the real-time time point and the target lifespan point.
[0164] In a preferred embodiment of this application, determining whether to modify the expected remaining lifetime includes:
[0165] Set the end time of each running cycle as the monitoring time node;
[0166] Obtain the feedback vibration packets of each vibration sensing point at the current monitoring time node;
[0167] The actual degradation curves of each vibration sensing point are generated based on all vibration feedback packets.
[0168] Generate the degradation deviation value for each vibration sensing point based on all actual degradation curves;
[0169] A corrected evaluation value d is generated based on all deterioration deviation values;
[0170] Preset correction evaluation value threshold D1;
[0171] If d > D1, generate a first-level correction instruction.
[0172] Specifically, the correction evaluation value threshold can be set based on historical parameters. When the real-time correction evaluation value is greater than the preset correction evaluation value threshold, it indicates that there is a serious deviation in the prediction of the remaining life of the power plant auxiliary equipment, and timely correction and prediction are required.
[0173] Specifically, a corresponding degradation deviation value is generated based on the difference between the actual degradation curve and the expected degradation curve of the vibration sensing point within the operating cycle corresponding to the current monitoring time node. The greater the difference, the greater the corresponding degradation deviation value. The mapping relationship between the two can be set according to historical parameters.
[0174] Specifically, generating the corrected evaluation value d includes:
[0175] Construct a secondary degradation feature package based on all actual degradation curves;
[0176] A secondary assessment strategy is generated based on the degradation assessment model and the secondary degradation feature package;
[0177] Generate a corrected evaluation value d;
[0178]
[0179] Where g is the correction compensation coefficient; n is the number of vibration sensing points; η 2i The influence factor for the i-th vibration sensing point is set according to the secondary evaluation strategy; s i θ1 is the degradation deviation value of the i-th vibration sensing point; U1 is the preset first conversion coefficient; θ1 is the number of auxiliary evaluation indicators; β i Let j be the influence factor of the i-th auxiliary evaluation index; i It is the reference value of the i-th auxiliary evaluation index generated based on all deterioration deviation values.
[0180] Specifically, the impact factor is the assessment impact factor in the secondary assessment strategy.
[0181] Specifically, based on all actual degradation curves, the degradation sub-state of each vibration sensing point is determined, and the corresponding evaluation sub-strategy for the evaluation scenario is selected as the secondary evaluation strategy.
[0182] Specifically, auxiliary evaluation indicators include, but are not limited to, the degradation rate of each vibration sensing point (the faster the rate, the larger the corresponding reference value), the overall average degradation rate, and other parameters that affect the accuracy of remaining lifetime prediction. By quantifying each auxiliary evaluation indicator, the reference values of each auxiliary evaluation indicator are made to fall within the same range, and the larger the reference value of each auxiliary evaluation indicator, the lower the accuracy of the current remaining lifetime prediction.
[0183] Specifically, the influence factors of each auxiliary evaluation indicator can be set according to their degree of influence on the accuracy of life prediction. The greater the degree of influence, the larger the reference value of the corresponding influence factor.
[0184] Specifically, by presetting a first conversion coefficient, the correction compensation coefficient g is made to be within a preset value range, and The larger the value of , the larger the corresponding correction compensation coefficient g will be. The mapping relationship between the two can be set according to historical parameters.
[0185] It is understandable that in the above embodiments, by periodically collecting vibration signals from each vibration sensing point and rolling corrections to the prediction results, the efficiency of early warning and maintenance of power plant auxiliary equipment deterioration risks is improved, ensuring the safe operation of power plant auxiliary equipment.
[0186] In a preferred embodiment of this application, it further includes:
[0187] Generate the risk assessment value f1 for the current monitoring time point based on all actual degradation curves;
[0188]
[0189] Where n is the number of vibration sensing points; η 2iThe influence factor for the i-th vibration sensing point is set according to the secondary evaluation strategy; c 2i It is the degradation risk value of the i-th vibration sensing point at the current monitoring time node, generated based on the actual degradation curve;
[0190] A second risk assessment threshold F2 is preset, and F2 < F1;
[0191] If f1 > F2, a Level 1 early warning instruction is generated at the current monitoring time point.
[0192] Specifically, the threshold for the second risk assessment value can be set based on historical parameters.
[0193] Specifically, when the real-time risk assessment value is greater than the preset second risk assessment value, it indicates that some vibration sensing points have a potential risk of being scrapped. They need to be repaired in a timely manner according to the first-level early warning instruction, thereby extending the overall service life of the power plant auxiliary equipment and improving the overall operation and maintenance efficiency.
[0194] Specifically, the rules for generating degradation risk values are the same as those in the aforementioned embodiments.
[0195] In another preferred embodiment of the auxiliary equipment remaining life prediction method based on vibration trend in any of the above preferred embodiments, this preferred embodiment provides an auxiliary equipment remaining life prediction method based on vibration trend, comprising:
[0196] The central control unit is used to set multiple vibration sensing points according to the structural parameters of the power plant's auxiliary equipment;
[0197] The monitoring unit includes multiple monitoring sub-modules, which are set at various vibration sensing points;
[0198] The monitoring unit is used to collect vibration signals from each vibration sensing point;
[0199] The central control unit includes:
[0200] The first processing module is used to build a lifetime prediction model;
[0201] The second processing module is used to acquire the initial vibration packets of each vibration sensing point and generate the expected remaining life of the power plant auxiliary equipment based on all the initial vibration packets and the preset life prediction model.
[0202] The correction module is used to obtain feedback vibration packets from each vibration sensing point according to a preset monitoring time node, and to determine whether to correct the expected remaining lifespan based on all monitoring data.
[0203] The first processing module is also used for:
[0204] Establish a sequence A of vibration sensing points, A = (a1, a2, ..., a...). i …a n), where a i Let be the i-th vibration sensing point; n is the number of vibration sensing points.
[0205] The original vibration database is constructed based on all vibration sensing points;
[0206] Based on the vibration sensing point sequence A, a is set sequentially. i For target perception point;
[0207] First-level correlation data of target sensing points are generated based on the original vibration database;
[0208] A degradation simulation model of the target sensing points is constructed based on the primary correlation data;
[0209] Deterioration simulation models for each vibration sensing point are generated sequentially.
[0210] A degradation assessment model is constructed based on all degradation simulation models and the original vibration database;
[0211] A lifetime prediction model is generated based on all degradation simulation models and degradation assessment models.
[0212] In a preferred embodiment of this application, the second processing module is further configured to:
[0213] Based on the vibration sensing point sequence A, a is set sequentially. i The sensing point to be evaluated;
[0214] The degradation simulation model of the sensing point to be evaluated is set as the target health model;
[0215] Obtain the initial vibration packet of the sensing point to be evaluated;
[0216] Generate the expected degradation curve of the sensing point to be evaluated based on the initial vibration package and the target health model;
[0217] The expected degradation curves for each vibration point are generated sequentially.
[0218] Establish multiple operating cycles;
[0219] Establish a periodic sequence T, T = (t1, t2, ..., tt3). i …t r ), where t i Let r be the i-th running cycle; r is the number of running cycles.
[0220] Risk assessment values for each operating cycle are generated sequentially based on the degradation assessment model.
[0221] The expected remaining lifespan of power plant auxiliary equipment is generated based on all risk assessment values.
[0222] According to the first concept of this application, multiple vibration sensing points are selected based on the structural parameters of power plant auxiliary equipment. By collecting the original vibration signals of each vibration sensing point, a corresponding degradation simulation model is constructed to predict the degradation state of each vibration sensing point, thereby achieving accurate prediction of the service life of power plant auxiliary equipment and providing data support for the operation and maintenance of power plant equipment.
[0223] According to the second concept of this application, by constructing a degradation assessment model, the expected degradation state of all vibration sensing points is analyzed in a linked manner, thereby improving the prediction accuracy of the remaining life of power plant auxiliary equipment. Furthermore, by periodically collecting vibration signals from each vibration sensing point, the prediction results are continuously corrected, thereby improving the early warning and maintenance efficiency of power plant auxiliary equipment degradation risks and ensuring the safe operation of power plant auxiliary equipment.
[0224] The above description is only a preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and substitutions can be made without departing from the technical principles of this application, and these improvements and substitutions should also be considered within the scope of protection of this application.
Claims
1. A method for predicting the remaining life of auxiliary equipment based on vibration trends, characterized in that, include: Multiple vibration sensing points are set according to the structural parameters of the power plant auxiliary equipment; The initial vibration packets of each vibration sensing point are obtained, and the expected remaining life of the power plant auxiliary equipment is generated based on all the initial vibration packets and the preset life prediction model. The feedback vibration packets of each vibration sensing point are obtained according to the preset monitoring time nodes, and the expected remaining life is determined based on all monitoring data.
2. The method for predicting the remaining life of auxiliary equipment based on vibration trends as described in claim 1, characterized in that, The preset lifespan prediction model includes: Establish a sequence A of vibration sensing points, A = (a1, a2, ..., a...). i …a n ), where a i Let be the i-th vibration sensing point; n is the number of vibration sensing points. The original vibration database is constructed based on all vibration sensing points; Based on the vibration sensing point sequence A, a is set sequentially. i For target perception point; First-level correlation data of target sensing points are generated based on the original vibration database; A degradation simulation model of the target sensing points is constructed based on the primary correlation data; Deterioration simulation models for each vibration sensing point are generated sequentially. A degradation assessment model is constructed based on all degradation simulation models and the original vibration database; A lifetime prediction model is generated based on all degradation simulation models and degradation assessment models.
3. The method for predicting the remaining life of auxiliary equipment based on vibration trends as described in claim 2, characterized in that, Construct a degradation assessment model, including: Based on the vibration sensing point sequence A, a is set sequentially. i For target perception point; Multiple degradation sub-states of the target sensing point are generated based on the degradation simulation model of the target sensing point; Multiple degraded sub-states are generated sequentially for each vibration sensing point; Multiple evaluation scenarios are constructed based on all degraded sub-states; Establish an evaluation scenario sequence B, B = (b1, b2, ..., bb) i …b m ), where b i Let m be the i-th evaluation scenario; m is the number of evaluation scenarios. b is set sequentially according to the evaluation scenario sequence B. i Target assessment scenario; A secondary association package for the target evaluation scenario is generated based on the original vibration database; Based on the secondary association package, generate evaluation sub-strategies for the target evaluation scenario; The evaluation sub-strategies for each evaluation scenario are generated sequentially, and a degradation evaluation model is generated based on all the evaluation sub-strategies.
4. The method for predicting the remaining life of auxiliary equipment based on vibration trends as described in claim 3, characterized in that, The expected remaining lifespan of power plant auxiliary equipment includes: Based on the vibration sensing point sequence A, a is set sequentially. i The sensing point to be evaluated; The degradation simulation model of the sensing point to be evaluated is set as the target health model; Obtain the initial vibration packet of the sensing point to be evaluated; Generate the expected degradation curve of the sensing point to be evaluated based on the initial vibration package and the target health model; The expected degradation curves for each vibration point are generated sequentially. Establish multiple operating cycles; Establish a periodic sequence T, T = (t1, t2, ..., tt3). i …t r ), where t i Let r be the i-th running cycle; r is the number of running cycles. Risk assessment values for each operating cycle are generated sequentially based on the degradation assessment model. The expected remaining lifespan of power plant auxiliary equipment is generated based on all risk assessment values.
5. The method for predicting the remaining life of auxiliary equipment based on vibration trends as described in claim 4, characterized in that, The expected remaining lifespan of power plant auxiliary equipment is generated based on all risk assessment values, including: t is set sequentially according to the operating cycle sequence T. i The target operating cycle; Generate a first-level degradation feature package for the target operating cycle based on all expected degradation curves; A first-level assessment strategy is generated based on the first-level degradation feature package and degradation assessment model; Generate the risk assessment value f for the target operating cycle; Where n is the number of vibration sensing points; η i The influence factor for the i-th vibration sensing point is set according to the primary evaluation strategy; c i It is the degradation risk value of the i-th vibration sensing point within the target operating cycle, generated based on the expected degradation curve; The first risk assessment threshold F1 is preset; If f > F1, set the target operating cycle as the risk cycle, and generate the expected remaining lifespan based on the risk cycle; If f < F1, generate the evaluation instruction for the next running cycle.
6. The method for predicting the remaining life of auxiliary equipment based on vibration trends as described in claim 5, characterized in that, Determining whether to revise the expected remaining lifetime includes: Set the end time of each running cycle as the monitoring time node; Obtain the feedback vibration packets of each vibration sensing point at the current monitoring time node; The actual degradation curves of each vibration sensing point are generated based on all vibration feedback packets. Generate the degradation deviation value for each vibration sensing point based on all actual degradation curves; A corrected evaluation value d is generated based on all deterioration deviation values; Preset correction evaluation value threshold D1; If d > D1, generate a first-level correction instruction.
7. The method for predicting the remaining life of auxiliary equipment based on vibration trends as described in claim 6, characterized in that, Generate the corrected evaluation value d, including: Construct a secondary degradation feature package based on all actual degradation curves; A secondary assessment strategy is generated based on the degradation assessment model and the secondary degradation feature package; Generate a corrected evaluation value d; Where g is the correction compensation coefficient; n is the number of vibration sensing points; η 2i The influence factor for the i-th vibration sensing point is set according to the secondary evaluation strategy; s i θ1 is the degradation deviation value of the i-th vibration sensing point; U1 is the preset first conversion coefficient; θ1 is the number of auxiliary evaluation indicators; β i Let j be the influence factor of the i-th auxiliary evaluation index; i It is the reference value of the i-th auxiliary evaluation index generated based on all deterioration deviation values.
8. The method for predicting the remaining life of auxiliary equipment based on vibration trends as described in claim 7, characterized in that, Also includes: Generate the risk assessment value f1 for the current monitoring time point based on all actual degradation curves; Where n is the number of vibration sensing points; η 2i The influence factor for the i-th vibration sensing point is set according to the secondary evaluation strategy; c 2i It is the degradation risk value of the i-th vibration sensing point at the current monitoring time node, generated based on the actual degradation curve; A second risk assessment threshold F2 is preset, and F2 < F1; If f1 > F2, a Level 1 early warning instruction is generated at the current monitoring time point.
9. A system for predicting the remaining service life of auxiliary equipment based on vibration trends, employing the method for predicting the remaining service life of auxiliary equipment based on vibration trends as described in any one of claims 1-8, characterized in that, include: The central control unit is used to set multiple vibration sensing points according to the structural parameters of the power plant's auxiliary equipment; The monitoring unit includes multiple monitoring sub-modules, which are located at various vibration sensing points; The monitoring unit is used to collect vibration signals from each vibration sensing point. The central control unit includes: The first processing module is used to build a lifetime prediction model; The second processing module is used to acquire the initial vibration packets of each vibration sensing point and generate the expected remaining life of the power plant auxiliary equipment based on all the initial vibration packets and the preset life prediction model. The correction module is used to obtain feedback vibration packets from each vibration sensing point according to a preset monitoring time node, and to determine whether to correct the expected remaining lifespan based on all monitoring data. The first processing module is also used for: Establish a sequence A of vibration sensing points, A = (a1, a2, ..., a...). i …a n ), where a i Let be the i-th vibration sensing point; n is the number of vibration sensing points. The original vibration database is constructed based on all vibration sensing points; Based on the vibration sensing point sequence A, a is set sequentially. i For target perception point; First-level correlation data of target sensing points are generated based on the original vibration database; A degradation simulation model of the target sensing points is constructed based on the primary correlation data; Deterioration simulation models for each vibration sensing point are generated sequentially. A degradation assessment model is constructed based on all degradation simulation models and the original vibration database; A lifetime prediction model is generated based on all degradation simulation models and degradation assessment models.
10. The auxiliary machine remaining life prediction system based on vibration trend as described in claim 9, characterized in that, The second processing module is also used for: Based on the vibration sensing point sequence A, a is set sequentially. i The sensing point to be evaluated; The degradation simulation model of the sensing point to be evaluated is set as the target health model; Obtain the initial vibration packet of the sensing point to be evaluated; Generate the expected degradation curve of the sensing point to be evaluated based on the initial vibration package and the target health model; The expected degradation curves for each vibration point are generated sequentially. Establish multiple operating cycles; Establish a periodic sequence T, T = (t1, t2, ..., tt3). i …t r ), where t i Let r be the i-th running cycle; r is the number of running cycles. Risk assessment values for each operating cycle are generated sequentially based on the degradation assessment model. The expected remaining lifespan of power plant auxiliary equipment is generated based on all risk assessment values.