An oxidation blower operation fault prediction and health management system

Abstract

The present application relates to the technical field of predictive health management of industrial equipment, in particular to an oxidation fan operation fault prediction and health management system, comprising: a data acquisition module for obtaining the operation environment parameters and downstream process load of the oxidation fan; a first processing module for determining the aerodynamic stability margin representing the operation stability of the fan; a second processing module for determining the corrosion fatigue crack propagation rate representing the cumulative damage of the blade; a health assessment module for determining the comprehensive health index representing the current state of the equipment, and outputting the corresponding health state grade according to the preset health state grading threshold; and an optimization control module for generating an adaptive optimization control strategy in response to the comprehensive health index and the health state grade. The present application overcomes the one-sidedness of the prior art which only focuses on a single physical field, can more accurately and comprehensively evaluate the true health state of the oxidation fan, and significantly improves the accuracy of fault prediction.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of predictive health management of industrial equipment, in particular to an oxidation fan operation fault prediction and health management system. BACKGROUND

[0002] In industrial production, oxidation fans are key power equipment to ensure the continuity of the process flow, and real-time monitoring of their health status is crucial;

[0003] The existing technology has significant one-sidedness in health monitoring of such equipment as oxidation fans; these methods usually only focus on the risks in a single physical field, for example, evaluating the aerodynamic instability risk of fan operation in isolation, or independently analyzing the fatigue damage of blade materials, without correlating the two;

[0004] However, this fragmented monitoring method ignores the strong coupling effect between the macro operating environment and the micro material damage; specifically, the instability of aerodynamic operation produces pressure pulsation, significantly accelerating the corrosion fatigue crack propagation of blade materials; this multi-physical field coupling effect is a key factor leading to accelerated equipment damage and reduced service life, but is ignored by traditional monitoring methods;

[0005] Therefore, how to establish a health assessment model that can integrate the coupling effects of aerodynamics, materials and other multi-physical fields, overcome the limitations of existing monitoring methods, and achieve accurate assessment and scientific prediction of fan health status, has become a technical problem to be solved in the field.

[0006] The above information disclosed in the above background section is only used to strengthen the understanding of the background of the present disclosure, and therefore it can include information that does not constitute prior art known to those of ordinary skill in the art. SUMMARY

[0007] To solve the above technical problems, the present application discloses an oxidation fan operation fault prediction and health management system, in particular, the technical solution of the present application is:

[0008] An oxidation fan operation fault prediction and health management system, comprising:

[0009] A data acquisition module for acquiring operating environment parameters and downstream process load of the oxidation fan;

[0010] A first processing module for determining an aerodynamic stability margin representing fan operation stability based on the operating environment parameters;

[0011] A second processing module for determining a corrosion fatigue crack propagation rate representing blade damage accumulation based on the aerodynamic stability margin and the operating environment parameters;

[0012] The health assessment module is configured to determine a comprehensive health index representing a current state of the device by combining the aerodynamic stability margin and the corrosion fatigue crack propagation rate, and output a corresponding health state level according to a preset health state grading threshold.

[0013] The optimization control module is configured to generate an adaptive optimization control strategy in response to the comprehensive health index and the health state level.

[0014] Preferably, the first processing module is configured to determine the aerodynamic stability margin based on the operating environment parameters, including:

[0015] The current outlet pressure and flow rate measured by the sensor and the air density in the operating environment parameters are called;

[0016] The surge pressure boundary function pre-stored in the system is queried based on the air density and flow rate to obtain the surge pressure boundary;

[0017] The aerodynamic stability margin is calculated by comparing the current outlet pressure with the surge pressure boundary.

[0018] Preferably, the second processing module is configured to determine the corrosion fatigue crack propagation rate based on the aerodynamic stability margin and the operating environment parameters, including:

[0019] The aerodynamic stability margin determined by the first processing module and the corrosion medium concentration in the operating environment parameters obtained by the data acquisition module are called;

[0020] The corrosion fatigue crack propagation rate is calculated based on the preset crack propagation model coupled with the aerodynamic stability, taking the aerodynamic stability margin as a dynamic stress influencing factor and combining the corrosion medium concentration.

[0021] Preferably, the health assessment module is configured to determine the comprehensive health index by combining the aerodynamic stability margin and the corrosion fatigue crack propagation rate, including:

[0022] The preset minimum allowable aerodynamic stability margin and maximum allowable crack propagation rate are called as evaluation benchmarks;

[0023] The deviation of the aerodynamic stability margin determined by the first processing module, the corrosion fatigue crack propagation rate determined by the second processing module, and the ideal safety point is calculated based on the weighted Euclidean distance, so as to determine the comprehensive health index.

[0024] Preferably, the health assessment module is configured to output a corresponding health state level according to a preset health state grading threshold, including:

[0025] The comprehensive health index determined by the health assessment module is compared with the preset first warning threshold and second warning threshold;

[0026] If the comprehensive health index is greater than or equal to the first early warning threshold, the health status level is determined as a safe state;

[0027] If the comprehensive health index is less than the first early warning threshold but greater than or equal to the second early warning threshold, the health status level is determined as a first-level early warning;

[0028] If the comprehensive health index is less than the second early warning threshold, the health status level is determined as a second-level early warning.

[0029] Preferably, the optimization control module comprises a damage evolution trend prediction unit for:

[0030] Based on the corrosion fatigue crack propagation rate determined by the second processing module, the damage accumulation in the future prediction time domain is time-integrated to obtain a predicted future crack size;

[0031] Based on the future crack size, the predicted health index at the future time is recalculated.

[0032] Preferably, the optimization control module comprises a control cost function construction unit for:

[0033] determining a process performance term for measuring process load deviation;

[0034] Based on the predicted health index determined by the damage evolution trend prediction unit, a health cost term for measuring the degree of equipment health degradation is determined;

[0035] The process performance term and the health cost term are combined to construct a double-target cost function.

[0036] Preferably, the optimization control module comprises an adaptive strategy generation unit for:

[0037] When the health status level is a safe state, a control strategy prioritizing meeting the process load instruction is generated;

[0038] When the health status level is a first-level early warning, a control strategy smoothing the change rate of the control instruction is generated;

[0039] When the health status level is a second-level early warning, a protective priority strategy dominated by the health cost term is generated, and the fan operating parameters are limited within the dynamic safety boundary.

[0040] Compared with the prior art, the present application has the following beneficial effects:

[0041] 1. The application establishes a coupling model between macroscopic aerodynamic instability and microscopic material damage, overcomes the one-sidedness of existing technologies that only focus on a single physical field, can more accurately and comprehensively evaluate the real health status of the oxidation fan, and significantly improves the accuracy of fault prediction. 2. The application not only can evaluate the current state of the equipment, but also can scientifically predict the future health trend based on the damage accumulation model, realizes the transformation from traditional post-fault maintenance to active predictive health management, and provides a forward-looking basis for maintenance decision-making. 3. The application builds a complete closed-loop management system from health assessment, trend prediction to optimization control, which can dynamically generate adaptive control strategies according to real-time health levels, and dynamically balances between meeting production process requirements and ensuring long-term health of the equipment. 4. The application actively avoids high-risk working conditions through forward-looking optimization control, effectively slows down the damage accumulation rate of fan blades and other key components, thereby prolonging the overall service life of the equipment, improving the operation reliability, and effectively ensuring the continuous and stable industrial production. BRIEF DESCRIPTION OF DRAWINGS

[0042] The application will be further explained in conjunction with the accompanying drawings and embodiments:

[0043] Figure 1 is a flow chart of the system of the application. DETAILED DESCRIPTION

[0044] In order to make the purpose, technical scheme and advantages of the application more clear and obvious, the application will be further described in detail in conjunction with specific embodiments. Embodiment 1:

[0045] Please refer to Figure 1 An oxidation fan operation fault prediction and health management system, comprising:

[0046] A data acquisition module for acquiring operation environment parameters and downstream process load of the oxidation fan;

[0047] A first processing module for determining an aerodynamic stability margin representing fan operation stability based on the operation environment parameters;

[0048] A second processing module for determining a corrosion fatigue crack propagation rate representing blade damage accumulation based on the aerodynamic stability margin and the operation environment parameters;

[0049] A health assessment module for determining a comprehensive health index representing the current state of the equipment by combining the aerodynamic stability margin and the corrosion fatigue crack propagation rate, and outputting a corresponding health status level according to a pre-set health status grading threshold;

[0050] An optimization control module for generating an adaptive optimization control strategy in response to the comprehensive health index and the health status level;

[0051] Embodiments of the present application provide an oxidation fan operation fault prediction and health management system; the system aims to solve the one-sidedness problem of health state monitoring of key equipment such as oxidation fan in the prior art, that is, only focusing on a single physical domain, while ignoring the acceleration effect of multi-physical field coupling on equipment damage; the system realizes accurate evaluation of fan health state, scientific prediction of future trend and closed-loop optimization control by building a complete cause-and-effect chain model from macro operating environment to micro material damage;

[0052] In a specific implementation scenario, the system includes the following core modules:

[0053] The data acquisition module aims to provide real-time and accurate raw data input for subsequent analysis and decision-making; in this embodiment, the module is realized by deploying multiple sensors at the inlet and outlet of the oxidation fan and the surrounding environment; for example, it continuously obtains the operating environment parameters of the oxidation fan, such as the air density at the inlet, which is converted by combining temperature and pressure sensors with altitude information The concentration of corrosive medium is measured by a chemical sensor And the working temperature of the key components is monitored by a temperature sensor At the same time, it also monitors the downstream process load This parameter reflects the requirements of production demand on fan output; in addition, the real-time speed of the fan is obtained through a speed sensor to determine the main stress cycle frequency, and these multi-dimensional data constitute the dynamic input source of the system model;

[0054] The first processing module aims to quantitatively evaluate the macro stability of the fan operation in real time; in this embodiment, the module focuses on evaluating the distance between the fan and the aerodynamic instability boundary based on operating environment parameters, and finally determines a core indicator: aerodynamic stability margin representing the stability of the fan operation; this margin value is a key precondition for subsequent coupling analysis;

[0055] The second processing module aims to reveal the internal influence mechanism of macro operating instability on micro material damage; in this embodiment, the innovation of the module lies in that it does not calculate material fatigue in isolation, but based on the aerodynamic stability margin calculated by the first processing module, operating environment parameters and the current crack size tracked by the system, it determines the corrosion fatigue crack propagation rate representing the cumulative damage of the blade through a coupling model;

[0056] a health assessment module, which aims to fuse risk information from different physical domains into a single, intuitive health indicator for quick understanding and response by operation personnel and control systems; in this embodiment, the module combines aerodynamic stability margin and corrosion fatigue crack propagation rate to calculate a comprehensive health index representing the current state of the equipment; the module converts the complex index value into a clear health state grade according to a preset health state grading threshold;

[0057] an optimal control module, which aims to proactively adjust the operation strategy of the fan based on the current health assessment result, realizing the transition from passive response to failure to active health management; in this embodiment, the module responds to the comprehensive health index and the health state grade to automatically generate an adaptive optimal control strategy by solving a double-objective optimization problem, achieving a dynamic balance between meeting process requirements and ensuring equipment health;

[0058] The system of this embodiment, through the cooperative work of the above-mentioned modules, for the first time establishes a complete closed loop of environment-aerodynamics-material damage-control in the field of oxidation fans; it not only can assess the current health status, but also can predict the future evolution trend, and automatically optimize the control strategy accordingly; compared with the prior art, the present application deeply couples the aerodynamic instability risk and the material damage risk, which were originally mutually disjointed, greatly improves the accuracy of fault prediction and the fineness of health management, thereby effectively prolongs the service life of the equipment and ensures the production continuity. Embodiment 2:

[0059] a first processing module for determining the aerodynamic stability margin based on the operating environment parameters, comprising:

[0060] calling the current outlet pressure and flow rate measured by the sensor, and the air density in the operating environment parameters;

[0061] based on the air density and the flow rate, querying the surge pressure boundary function pre-stored in the system to obtain the surge pressure boundary;

[0062] by comparing the current outlet pressure with the surge pressure boundary, the aerodynamic stability margin is calculated;

[0063] Based on embodiment 1, the first processing module, the core purpose of which is to provide a real-time, quantitative assessment of the aerodynamic stability risk of the fan; in this embodiment, the module determines the aerodynamic stability margin by the following steps:

[0064] To determine the aerodynamic stability margin, the module calls the current outlet pressure and flow rate measured by the sensor, and the air density in the operating environment parameters;

[0065] It refers to the current outlet pressure of the fan, and its function is to represent the work capacity of the fan to the downstream system, which is measured in real time by the pressure sensor installed in the fan outlet pipeline;

[0066] It refers to the current volume flow of the fan, and its function is to represent the conveying capacity of the fan, which is measured in real time by the flow meter installed in the fan pipeline;

[0067] It refers to the air density at the inlet of the fan, and its function is to correct the performance benchmark of the fan under different environmental conditions, which is calculated according to environmental temperature and altitude and other parameters through a standard atmospheric physical model;

[0068] The module is based on air density and flow query the surge pressure boundary function pre-stored in the system obtain the surge pressure boundary;

[0069] surge pressure boundary It refers to the highest outlet pressure limit at which the fan can operate stably under the conditions of a specific air density and flow ; this functional relationship is determined in advance through performance testing before the device is shipped or high-precision computational fluid dynamics simulation, and is stored in the system memory in the form of a data table or a function to ensure the efficiency of the query; based on the surge pressure boundary, the module calculates the aerodynamic stability margin by comparing the current outlet pressure with the surge pressure boundary This calculation follows the standard definition in the field of aerodynamics, and is realized through the following formula:

[0070]

[0071] wherein, It refers to the aerodynamic stability margin, which is a dimensionless percentage, and its physical meaning is the relative distance of the current operating point from the surge boundary; the smaller the value, the closer the fan is to the unstable state; this value is calculated in this step and is passed as the core output to the second processing module. Embodiment 3:

[0072] The second processing module is configured to determine the corrosion fatigue crack propagation rate based on the aerodynamic stability margin and the operating environment parameters, and includes:

[0073] The aerodynamic stability margin determined by the first processing module and the corrosion medium concentration in the operating environment parameters obtained by the data acquisition module are called;

[0074] Based on the preset crack propagation model coupled with aerodynamic stability, the aerodynamic stability margin is taken as a dynamic stress influencing factor, and the corrosion medium concentration is combined to calculate the corrosion fatigue crack propagation rate;

[0075] The core innovation of the second processing module in this embodiment is that it does not use the traditional fatigue model considering only mechanical stress, but establishes a damage accumulation model coupled with macroscopic aerodynamic behavior. The purpose is to accurately simulate the acceleration effect of the synergistic action of airflow pulsation and corrosion environment on the microcrack propagation of the blade under real operating conditions.

[0076] The specific implementation of the module is as follows:

[0077] The module calls the aerodynamic stability margin determined by the first processing module and the corrosion medium concentration in the operating environment parameters obtained by the data acquisition module

[0078] Based on the foregoing inputs, the module uses a preset crack propagation model coupled with aerodynamic stability, takes the aerodynamic stability margin as a dynamic stress influencing factor, and combines the corrosion medium concentration to calculate the corrosion fatigue crack propagation rate. The internal logic is that when the fan operating point approaches the surge boundary, that is, The airflow pulsation in the blade passage will be dramatically enhanced, and this high-frequency pressure pulsation will generate an additional dynamic alternating stress on the blade surface. This stress is a key damage factor that is not considered in the traditional model.

[0079] This embodiment improves the classic Paris formula and proposes the following coupled model:

[0080]

[0081] wherein, The corrosion fatigue crack propagation rate, with the dimension of length / cycle, is calculated by the formula. It represents the propagation length of the microcrack tip on the blade under one stress cycle.

[0082] The material constant, whose dimension needs to be coordinated with the overall formula, is calibrated by fitting the experimental data obtained from the standard corrosion fatigue experiment of the material used for the fan blade.

[0083] The mechanical stress intensity factor, with the dimension of is mainly determined by the centrifugal force generated by the rotation of the blade and the stable aerodynamic load. It is calculated by the pre-set finite element analysis response surface model in the system or the following standard empirical formula according to the current fan speed and operating conditions: wherein is the average stress of the key part of the blade calculated according to the rotating speed, is a correction factor depending on the crack and the geometry of the blade, is the current crack size;

[0084] is the aerodynamic stability margin, dimensionless, calculated by the first processing module in real time;

[0085] is the aerodynamic-damage coupling factor, dimensionless, calculated by the first processing module in real time; is the aerodynamic-damage coupling factor, dimensionless, calculated by the first processing module in real time; its physical meaning is the size of the additional dynamic stress intensity factor excited by the airflow fluctuation when the aerodynamic stability margin drops to a reference unit; this parameter is the key innovative parameter of the present application, and its value needs to be calibrated for a specific type of fan;

[0086] is the concentration of the corrosion medium, for example, mg / m³, measured by the chemical sensor of the data acquisition module in real time;

[0087] is the corrosion sensitivity coefficient, dimensionless, calibrated by material experimental data; is the corrosion sensitivity coefficient, dimensionless, calibrated by material experimental data; is the corrosion sensitivity coefficient, dimensionless, calibrated by material experimental data;

[0088] To further clarify the calibration process of the model parameters and ensure their implementability, the present embodiment makes the following supplementary explanations:

[0089] To calibrate the aerodynamic-damage coupling factor a series of fluid-structure coupling simulations can be performed; in each simulation, a specific and constant aerodynamic stability margin is set, and the additional dynamic stress intensity factor excited thereby is calculated; by regression analysis, for example, least squares fitting of the relationship , the value of can be determined;

[0090] It should be noted that the inverse relationship here is a first-order approximation of the complex aerodynamic-elastic effect, aiming to capture the core trend of damage acceleration reduction; in scenarios requiring higher precision, this item can also be replaced by a more complex nonlinear function calibrated by experiments or simulations At the same time, the aerodynamic influence term and the mechanical stress term Linear superposition is also an approximation process aiming to simplify the calculation, which can be replaced by a more complex nonlinear coupling function calibrated by experiment or simulation in scenarios requiring higher accuracy

[0091] To ensure the numerical stability of the model, a practical minimum threshold value is set for the value of For example, 0.5%; when the calculated is less than this threshold value, the model is uniformly calculated and directly triggers the highest level of stall warning. This avoids the model singularity problem when approaches zero;

[0092] To calibrate the material constant and the corrosion sensitivity coefficient A series of standard corrosion fatigue experiments need to be conducted on the blade material sample; in the experiment, different constant stress intensity factor ranges and constant corrosion medium concentrations are controlled, and the corresponding crack propagation rates are recorded Based on a large number of experimental data points, the parameter combination that best describes the material characteristics can be fitted through multivariate nonlinear regression analysis

[0093] In a more precise model, the material constant and the corrosion sensitivity coefficient can be regarded as functions of temperature , that is The functional relationship needs to be calibrated through material experiments at different temperatures.

[0094] Embodiment 4:

[0095] The health assessment module is used to determine the comprehensive health index by combining the aerodynamic stability margin and the corrosion fatigue crack propagation rate, including:

[0096] The preset minimum allowed aerodynamic stability margin and the maximum allowed crack propagation rate are called as the evaluation benchmark;

[0097] Based on the weighted Euclidean distance, the deviation of the aerodynamic stability margin determined by the first processing module and the corrosion fatigue crack propagation rate determined by the second processing module from the ideal safety point is calculated, so as to determine the comprehensive health index;

[0098] The health assessment module is used to output the corresponding health state level according to the preset health state grading threshold, including:

[0099] The comprehensive health index determined by the health assessment module is compared with preset first and second early warning thresholds;

[0100] If the comprehensive health index is greater than or equal to the first early warning threshold, the health status level is determined as a safe state;

[0101] If the comprehensive health index is less than the first early warning threshold but greater than or equal to the second early warning threshold, the health status level is determined as a first-level early warning;

[0102] If the comprehensive health index is less than the second early warning threshold, the health status level is determined as a second-level early warning;

[0103] In this embodiment, on the basis of Embodiment 3, to convert the multi-dimensional risk assessment result into a unified and easy-to-decide index, the health assessment module realizes this by calculating a comprehensive health index and performing state grading;

[0104] The calculation process of this module calls preset minimum allowable aerodynamic stability margin and maximum allowable crack propagation rate as evaluation benchmarks;

[0105] The minimum allowable aerodynamic stability margin refers to the minimum safety threshold of the aerodynamic stability margin set according to design specifications and safe operation experience, which is set according to industry standards or equipment design manuals, for example, set to 15%;

[0106] The maximum allowable crack propagation rate refers to the highest allowable value of the crack propagation rate determined according to the material fracture toughness, design life and safety factor, which is determined through fracture mechanics analysis combined with safety margin requirements;

[0107] On this basis, the module calculates the deviation of the aerodynamic stability margin determined by the first processing module, the corrosion fatigue crack propagation rate determined by the second processing module and the ideal safety point based on the weighted Euclidean distance, thereby determining the comprehensive health index The technical motivation of this algorithm is that it can intuitively measure the distance between the current state point and the absolute safe state in the multi-dimensional risk space; the calculation formula is as follows:

[0108]

[0109] By using the function, it is ensured that the calculation result of the comprehensive health index will not be lower than 0, so that the value range is strictly kept in the interval;

[0110] wherein, a comprehensive health index, dimensionless, whose value ranges between 0 and 1, and the closer to 1 indicates the more healthy the device is;

[0111] a weight coefficient, dimensionless, and satisfying is set according to the experience of operation and maintenance experts or specific working conditions; for example, during the stage of severe fluctuation of downstream process load, the weight of can be dynamically adjusted to focus on the attention to pneumatic stability;

[0112] After the comprehensive health index is calculated, the module immediately compares it with the preset threshold to output discrete and explicit health grades; the module compares the comprehensive health index with the preset first warning threshold and second warning threshold; in this embodiment, the first warning threshold is set to 0.8, and the second warning threshold is set to 0.5; the setting of these thresholds is determined on the basis of statistical analysis of a large amount of historical operation data and failure cases, aiming to balance the sensitivity and reliability of the warning;

[0113] The grading logic is as follows:

[0114] If the comprehensive health index is greater than or equal to the first warning threshold , the health state grade is determined as the safe state;

[0115] If the comprehensive health index is less than the first warning threshold but greater than or equal to the second warning threshold , the health state grade is determined as the first-level warning;

[0116] If the comprehensive health index is less than the second warning threshold , the health state grade is determined as the second-level warning.

[0117] Embodiment 5:

[0118] The optimization control module includes a damage evolution trend prediction unit, configured to:

[0119] based on the corrosion fatigue crack propagation rate determined by the second processing module, time-integrating the damage accumulation in the future prediction time domain to obtain the predicted future crack size;

[0120] based on the future crack size, re-calculating the predicted health index at the future time;

[0121] The optimization control module includes a control cost function construction unit, configured to:

[0122] determining a process performance term for measuring the process load deviation;

[0123] determine a health cost term for measuring the degree of health degradation of the equipment based on the predicted health index determined by the damage evolution trend prediction unit;

[0124] combine the process performance term and the health cost term to construct a dual-objective cost function;

[0125] The optimization control module includes an adaptive strategy generation unit for:

[0126] when the health status level is the safe state, generating a control strategy that prioritizes meeting the process load instruction;

[0127] when the health status level is the first level of warning, generating a control strategy that smooths the change rate of the control instruction;

[0128] when the health status level is the second level of warning, generating a protective priority strategy dominated by the health cost term and limiting the fan operating parameters within the dynamic safety boundary;

[0129] After determining the current health status level, the optimization control module starts a forward-looking, closed-loop health management process; this process logically includes three closely linked links of future health status prediction, control cost quantitative construction, and adaptive control strategy generation;

[0130] In the prediction link, the purpose of the damage evolution trend prediction unit is to forwardly deduce the influence of a specific control strategy on the future health status of the equipment; based on the current corrosion fatigue crack propagation rate determined by the second processing module time-integrate the damage accumulation in the future prediction time domain to obtain the predicted future crack size The physical basis of this step is to time-integrate the rate to obtain the cumulative amount:

[0131]

[0132] wherein, the predicted crack size, in units of length, is the core output of this link;

[0133] the crack size at the current time, in units of length; at the first time of system operation, it is set to a standard initial micro-defect size determined based on material purity and manufacturing process In subsequent operation, the value of is periodically updated by a data fusion unit: based on the predicted value of the model in the last period, and periodically or when new non-destructive testing data is received, Kalman filtering or similar state estimation method is used to fuse the actual measurement value with the model predicted value, thereby calibrating and updating the current crack size , effectively avoiding the error accumulation of pure model prediction;

[0134] The instantaneous crack propagation rate is calculated in real time by the model of the second processing module according to the predicted future working conditions;

[0135] The principal stress cycle frequency, with units of Its physical meaning is the number of stress cycles per second that the fan blade experiences, which is obtained from the control system command or the speed sensor;

[0136] The prediction time domain, with units of time, refers to the length of time in the future that needs to be predicted;

[0137] Based on the predicted future crack size and the estimation of future working conditions, this unit re-substitutes it into the aforementioned model to re-calculate the predicted health index at the future time

[0138] To achieve forward-looking optimization, this module is built-in with a dynamic performance response model of the oxidation fan; this model can predict the operating parameters of the fan in the future time domain, such as outlet pressure and flow and the final downstream process load based on a series of future fan target speeds as input Based on these predicted operating parameters, the system can further call the models of the first and second processing modules to calculate the predicted health index These predicted values provide the basis for calculating the cost function; this dynamic performance response model can be a first or second order transfer function model based on physical mechanisms, or a nonlinear autoregressive model or neural network model trained using historical operating data through system identification methods;

[0139] In the quantitative construction link, the control cost function construction unit creates a mathematical framework for evaluating the pros and cons of different alternative control strategies based on the predicted future health index ; this unit constructs a double-objective cost function through the following formula

[0140]

[0141] is the comprehensive performance score of an alternative control sequence u in the future prediction time domain , the smaller the value, the better; where is the prediction horizon for evaluating the control sequence, whose unit is time, and its value is set according to the response speed of the control system and the characteristics of the process flow;

[0142] wherein, is the process performance term for measuring the deviation of the process load, which penalizes any behavior deviating from the production instruction; is the load target value of the downstream process demand, and is the actual process load output predicted by the model under the control sequence ; is the process load reference value for normalization, such as the rated load or the maximum load, which serves to make the process performance term dimensionless;

[0143] is the health cost term for measuring the degree of deterioration of the equipment health, which is determined based on the predicted health index , and penalizes any control behavior that causes the future health condition to deteriorate;

[0144] To achieve adaptive control, the weight coefficient is designed to dynamically associate with the current health index , and satisfies wherein is a constant; for example, can be set as , and is a preset constant; when the equipment health, i.e. , is high, is small, and the cost function is mainly satisfied with the process; when the health deteriorates, i.e. , is low, increases sharply, forcing the optimization algorithm to give priority to the health cost term;

[0145] In the strategy generation link, the adaptive strategy generation unit solves the optimal control sequence that minimizes the cost function by using numerical optimization algorithms such as model predictive control (MPC), sequence quadratic programming (SQP), or genetic algorithm, etc. in each control period, and executes differentiated control output in combination with the current health status level;

[0146] When the health status level is the safe state, the weight is low, and the optimization result is generated to give priority to the control strategy of satisfying the process load instruction ;

[0147] When the health status level is the first-level warning, Weight increases, the optimization algorithm generates a smooth control instruction change rate control strategy, for example, the regulation slope of the fan speed is limited within 50%-80% of the normal value to avoid sharp parameter change transiently lowering value;

[0148] When the health status level is a secondary warning, The weight dominates the cost function, and the optimization algorithm generates a protective priority strategy dominated by the health cost term; the system will force the fan operating parameters to be limited within a dynamic safety boundary calculated in real time according to the predicted health index For example, temporarily reduce the maximum allowable speed or load response capability by 20%-40%, and issue an alarm;

[0149] The model framework proposed in this embodiment focuses on the core damage mechanism of aerodynamic-corrosion-fatigue coupling, providing an innovative solution for fine health management. It should be noted that this model is an extensible framework, which can further integrate other key influencing factors in future deployment; for example, by modeling the corrosion sensitivity coefficient and material constant as a function of working temperature , thermal effects can be included in damage assessment; by introducing vibration sensor data, additional effects of other mechanical vibration sources on fatigue life can be identified and quantified in addition to aerodynamic pulsation; this modular expansion capability ensures the practicality and comprehensiveness of the system in dealing with more complex industrial scenarios.

[0150] The above are only preferred embodiments of the present application and are not intended to limit the protection scope of the present application; any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

[0151] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present application and are not limiting, although the present application has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present application can be modified or replaced equivalently without departing from the spirit and scope of the technical solutions of the present application.

Claims

1. An oxidation blower operation fault prediction and health management system, characterized by, The method comprises the following steps: a data acquisition module is configured to acquire the operating environment parameters of the oxidation fan and the downstream process load; a first processing module is configured to determine the aerodynamic stability margin representing the operating stability of the fan based on the operating environment parameters; a second processing module is configured to determine the corrosion fatigue crack propagation rate representing the cumulative damage of the blade based on the aerodynamic stability margin and the operating environment parameters; a health assessment module is configured to determine the comprehensive health index representing the current state of the device by combining the aerodynamic stability margin and the corrosion fatigue crack propagation rate, and output the corresponding health status level according to the preset health status grading threshold; an optimization control module is configured to generate an adaptive optimization control strategy in response to the comprehensive health index and the health status level. The first processing module is configured to determine the aerodynamic stability margin based on the operating environment parameters, comprising: calling the current outlet pressure and flow rate measured by the sensor, and the air density in the operating environment parameters; querying the surge pressure boundary function pre-stored in the system based on the air density and the flow rate to obtain the surge pressure boundary; comparing the current outlet pressure with the surge pressure boundary to calculate the aerodynamic stability margin. The second processing module is configured to determine the corrosion fatigue crack propagation rate based on the aerodynamic stability margin and the operating environment parameters, comprising: calling the aerodynamic stability margin determined by the first processing module and the corrosion medium concentration in the operating environment parameters acquired by the data acquisition module; based on the preset crack propagation model coupled with the aerodynamic stability, taking the aerodynamic stability margin as a dynamic stress influencing factor, combining the corrosion medium concentration, and calculating to obtain the corrosion fatigue crack propagation rate.

2. The oxidation blower operational fault prognostics and health management system of claim 1, wherein, The health assessment module is configured to determine the comprehensive health index by combining the aerodynamic stability margin and the corrosion fatigue crack propagation rate, comprising: calling the preset minimum allowable aerodynamic stability margin and the maximum allowable crack propagation rate as the evaluation reference; based on the weighted Euclidean distance, calculating the deviation degree of the aerodynamic stability margin determined by the first processing module, the corrosion fatigue crack propagation rate determined by the second processing module, and the ideal safety point, thereby determining the comprehensive health index.

3. The oxidation blower operational fault prediction and health management system of claim 2, wherein, The health assessment module is configured to output the corresponding health status level according to the preset health status grading threshold, comprising: comparing the comprehensive health index determined by the health assessment module with the preset first warning threshold and second warning threshold; if the comprehensive health index is greater than or equal to the first warning threshold, the health status level is determined as the safe state; if the comprehensive health index is less than the first warning threshold but greater than or equal to the second warning threshold, the health status level is determined as the first warning level; if the comprehensive health index is less than the second warning threshold, the health status level is determined as the second warning level.

4. The oxidation blower operational fault prediction and health management system of claim 3, wherein, The optimization control module includes a damage evolution trend prediction unit, which is configured to: based on the corrosion fatigue crack propagation rate determined by the second processing module, time-integrating the damage accumulation in the future prediction time domain to obtain the predicted future crack size; based on the future crack size, recalculating to obtain the predicted health index at the future time.

5. The oxidation blower operational fault prediction and health management system of claim 4, wherein, The optimization control module includes a control cost function construction unit, which is configured to: determine a process performance term for measuring process load deviation; determine a health cost term for measuring the degree of equipment health deterioration based on the predicted health index determined by the damage evolution trend prediction unit; combine the process performance term and the health cost term to construct a double-target cost function.

6. The oxidation blower operational fault prediction and health management system of claim 5, wherein, The optimization control module includes an adaptive strategy generation unit, configured to: when the health state level is the safe state, generate a control strategy that prioritizes meeting the process load instruction; when the health state level is the first-level early warning, generate a control strategy that smooths the change rate of the control instruction; when the health state level is the second-level early warning, generate a protective priority strategy dominated by the health cost term, and limit the fan operating parameters within the dynamic safety boundary.

Images