Airborne equipment hybrid operation and maintenance method, system, equipment and medium

Abstract

The invention belongs to the technical field of aviation equipment health management and intelligent operation and maintenance, and provides an airborne equipment hybrid operation and maintenance method, system and device and a medium, and the method comprises the steps: constructing a degradation model of airborne equipment; determining parameters of the degradation model through historical degradation sample data; state monitoring is carried out on the airborne equipment, a current equipment degradation value is obtained, and the average residual life is calculated through a degradation model and parameters thereof; an optimization algorithm is adopted to solve an optimal parameter combination enabling the long-term unit time cost to be minimum, and the optimal parameter combination is configured to the operation and maintenance measure model; and according to the current equipment degradation value, the average residual life and the historical operation and maintenance record of the airborne equipment, the operation and maintenance measure model and the decision threshold are adopted to judge the operation and maintenance measure type and generate a corresponding decision instruction. According to the method, the ELE is introduced to quantify the repair benefit, so that cooperation of multiple operation and maintenance measures and parameter self-optimization are realized, the operation and maintenance cost is remarkably reduced, and the availability of equipment is improved.

Description

TECHNICAL FIELD

[0001] The present application belongs to the field of aviation equipment health management and intelligent operation and maintenance, and relates to an airborne equipment hybrid operation and maintenance method, system, device and medium based on equipment degradation process modeling and expected life assessment. BACKGROUND

[0002] Modern military and civil aircraft have very high requirements for the reliability, availability and safety of airborne equipment. Traditional operation and maintenance strategies mainly include periodic replacement (TBM) and corrective maintenance (CM). TBM is prone to cause "over maintenance", resulting in waste of resources; CM often causes task interruption and high unplanned parking loss due to sudden failure.

[0003] To improve efficiency, condition-based maintenance (CBM) monitors equipment status through sensors and intervenes in advance. However, existing CBM mostly relies on static thresholds or simple degradation models (such as linear or exponential models), which are difficult to accurately depict the nonlinear and random degradation behavior of airborne equipment under complex working conditions, especially for "accelerated degradation" equipment (such as bearing wear and insulation aging), whose degradation rate accelerates with damage accumulation, thereby underestimating the remaining life and causing decision lag.

[0004] In recent years, the Gamma random process has been used for degradation modeling due to its non-decreasing property and modeling flexibility, but related researches are mostly limited to a single maintenance strategy (replacement only or repair only), which lacks a collaborative optimization mechanism for detection, repair, protective replacement and corrective replacement. In particular, "repair" is a low-cost but imperfect means, and its decision has long relied on experience without quantitative basis.

[0005] In addition, current methods generally ignore the expected life extension (ELE) - the actual gain of remaining life by maintenance operation. ELE is a key indicator for judging "whether it is worth repairing": when ELE is too low, the cost-effectiveness of repair is not as good as replacement, and when it is high enough, it can significantly extend the life and reduce the cost. However, how to couple ELE with the cost model including unplanned parking loss and systematically optimize the decision threshold remains an industry problem.

[0006] Therefore, there is an urgent need for a hybrid operation and maintenance method that can accurately model the degradation process, quantify the maintenance benefit and automatically optimize the parameters, to realize the intelligent, fine and economic unification of airborne equipment operation and maintenance. SUMMARY

[0007] To solve the technical problems of insufficient degradation modeling capability, single maintenance strategy, lack of quantitative basis for repair decision, dependence on manual experience for parameter configuration and insufficient consideration of unplanned parking loss in the prior art, the present application provides a hybrid operation and maintenance method for airborne equipment.

[0008] The method realizes the collaborative decision of multiple types of operation and maintenance actions and the automatic optimization configuration of key decision parameters by constructing a Gamma random process model capable of characterizing the nonlinear acceleration degradation characteristics, introducing the expected life extension (ELE) as a quantitative criterion for repair benefit, and establishing a long-term cost optimization framework that integrates detection, repair, protective replacement, and corrective replacement measures and includes unplanned downtime losses. Specifically, the method comprises the following steps:

[0009] S1, based on the Gamma random process, a degradation model of the airborne device is constructed, which is a non-decreasing random process for characterizing the evolution law of the device degradation degree over time;

[0010] S2, the parameters of the degradation model are determined by using a parameter estimation method through historical degradation sample data of the airborne device;

[0011] S3, the state of the airborne device is monitored by using an airborne sensor to obtain the current device degradation value, and the average remaining life of the airborne device under the current device degradation value is calculated through the degradation model and its parameters;

[0012] S4, a long-term unit time cost model is constructed, the decision threshold is used as the optimization variable, and an optimization algorithm is used to solve the optimal parameter combination that minimizes the long-term unit time cost, and the optimal parameter combination is configured to the operation and maintenance measure model;

[0013] S5, according to the current device degradation value, the average remaining life and the historical operation and maintenance record of the airborne device, the operation and maintenance measure model and the decision threshold are used to determine the type of operation and maintenance measure and generate corresponding decision instructions.

[0014] Further, the degradation increment of the airborne device in the time interval [t1-t2] is From the Gamma distribution, the probability density function is:

[0015]

[0016] wherein, is the device degradation value at t2, is the device degradation value at t1, f α·Δt,β (Δx) is the probability density corresponding to the arc increment Δx; Γ(·) is the Gamma function; α and β are the shape parameter and inverse scale parameter of the Gamma distribution, respectively; Δt=t2-t1 is the interval length.

[0017] Further, in step S2, the historical degradation sample data includes no less than 20 samples, and each sample includes an initial degradation value, an initial time, a current device degradation value, and a current time.

[0018] The parameter of the degradation model is solved by constructing a likelihood function of the historical degradation sample data and maximizing the likelihood function.

[0019] Further, in step S3, the calculation formula of the average remaining life is:

[0020]

[0021] wherein x b is the current equipment degradation value, MRL(x b ) is the average remaining life at the current time t b and the equipment degradation value is x b , m is the demarcation point of the degradation rate change, and are the Gamma cumulative distribution functions corresponding to the parameters, is the Gamma probability density function corresponding to the parameters, u and τ are the independent variables of the integral, and L is the preset failure threshold.

[0022] Further, in step S4, the expression of the long-term unit time cost model is:

[0023]

[0024] wherein C ∞ is the unit time cost, N i (t), N prc (t), N crc (t), N rpr (t) respectively represent the number of detections, protective replacements, corrective replacements and repairs of the airborne equipment within the time [0, t]; D(t) is the cumulative length of unplanned parking caused by failure of the airborne equipment during [0, t]; C i , C prc , C crc , C rpr , C o are the weights of the detections, protective replacements, corrective replacements and repairs of the airborne equipment.

[0025] Further, in step S4, the decision threshold includes a repair decision threshold and a protective replacement threshold, the repair decision threshold is used to judge whether the expected life extension amount meets the repair condition, and the protective replacement threshold is used to judge whether the equipment degradation state reaches the preventive replacement critical point.

[0026] Still further, in step S5, the logic of generating the decision instruction includes:

[0027] The difference between the current equipment degradation value and the random equipment degradation value after repair is calculated as the expected extended lifespan, and the expected extended lifespan is defined as the increment of the average remaining lifespan of the airborne equipment after the repair is performed.

[0028] When the expected lifespan extension is greater than the repair determination threshold, a decision instruction to perform repair is generated;

[0029] When the expected lifespan extension is less than or equal to the repair decision threshold, and the current equipment degradation value is greater than or equal to the protective replacement threshold, a decision instruction to perform protective replacement is generated.

[0030] When the current equipment degradation value is greater than or equal to a preset fault threshold, it is determined that the airborne equipment has failed, and a decision instruction to perform corrective replacement is generated.

[0031] This invention also provides a hybrid operation and maintenance system for airborne equipment, including a degradation modeling module, a parameter estimation module, a reliability assessment module, a decision generation module, and a strategy optimization module.

[0032] Among them, the degradation modeling module is used to construct a degradation model of airborne equipment based on the Gamma stochastic process. The degradation model is a non-decreasing stochastic process used to characterize the evolution of equipment degradation over time.

[0033] The parameter estimation module is used to determine the parameters of the degradation model by using the historical degradation sample data of the airborne equipment and employing parameter estimation methods.

[0034] The reliability assessment module is used to monitor the condition of the airborne equipment using airborne sensors, obtain the current equipment degradation value, and calculate the average remaining life of the airborne equipment under the current equipment degradation value using the degradation model and its parameters.

[0035] The decision generation module is used to construct a long-term unit time cost model. Using the decision threshold as the optimization variable, it uses an optimization algorithm to solve for the optimal parameter combination that minimizes the long-term unit time cost, and then configures the optimal parameter combination into the operation and maintenance measures model.

[0036] The strategy optimization module is used to determine the type of maintenance measures and generate corresponding decision instructions based on the current equipment degradation value, the average remaining lifespan, and the historical maintenance records of the airborne equipment, using the maintenance measure model and the decision threshold.

[0037] This invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements any of the above-mentioned hybrid operation and maintenance methods for airborne equipment, thereby solving the technical problems in the prior art, such as insufficient degradation modeling capabilities, single operation and maintenance strategies, lack of quantitative basis for repair decisions, reliance on manual experience for parameter configuration, and insufficient consideration of unplanned downtime losses.

[0038] This invention also provides a computer-readable storage medium storing a computer program that executes any of the above-described hybrid operation and maintenance methods for airborne equipment, in order to solve the technical problems existing in the prior art, such as insufficient degradation modeling capabilities, single operation and maintenance strategies, lack of quantitative basis for repair decisions, reliance on manual experience for parameter configuration, and insufficient consideration of unplanned downtime losses.

[0039] Compared with the prior art, the beneficial effects that at least one technical solution adopted in the embodiments of this specification can achieve include at least:

[0040] 1. The method of the present invention can effectively determine the degree and trend of equipment degradation at any given time;

[0041] 2. This invention implements a method for calculating equipment reliability parameters based on a degradation model, which can provide maintenance personnel with accurate expected equipment lifespan and failure probability;

[0042] 3. This invention can formulate appropriate maintenance measures based on the current deterioration state and historical state of the equipment, which can better reflect the actual situation of equipment operation and maintenance, and further improve the economy and reliability of airborne equipment operation and maintenance. Attached Figure Description

[0043] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0044] Figure 1 This is a flowchart of the hybrid operation and maintenance method for airborne equipment according to the present invention;

[0045] Figure 2 This refers to the degradation process of airborne equipment;

[0046] Figure 3 The MRL variation curves of airborne equipment under different initial degradation levels are shown.

[0047] Figure 4 A schematic diagram for equipment repair;

[0048] Figure 5 This is a schematic diagram illustrating the evolution of equipment degradation based on maintenance rules.

[0049] Figure 6 This is an architecture diagram of the hybrid operation and maintenance system for airborne equipment of the present invention;

[0050] Among them, 601 is the degradation modeling module; 602 is the parameter estimation module; 603 is the reliability assessment module; 604 is the decision generation module; and 605 is the strategy optimization module. Detailed Implementation

[0051] The embodiments of this application will now be described in detail with reference to the accompanying drawings.

[0052] The following specific examples illustrate the implementation of this application. Those skilled in the art can easily understand other advantages and effects of this application from the content disclosed in this specification. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. This application can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of this application. It should be noted that, in the absence of conflict, the following embodiments and features of the embodiments can be combined with each other. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0053] This invention describes the abbreviations and key terms used below:

[0054] CM (Corrective Maintenance): Also known as reactive maintenance. This refers to maintenance and repair performed only after equipment has partially or completely failed.

[0055] TBM (Time Based Maintenance): A maintenance strategy based on time, also known as scheduled maintenance. This involves performing maintenance on airborne equipment at predetermined time intervals according to the aircraft's actual schedule and arrangements.

[0056] CBM (Condition Based Maintenance): A condition-based maintenance strategy. This involves analyzing the historical and current state of equipment to predict the development trend of potential problems and to perform maintenance before irreversible serious accidents occur.

[0057] MRL (Mean Residual Life): Average Remaining Life

[0058] ELE (Extended Life Expectancy): Expected extended lifespan. This refers to the expected extension of the average remaining lifespan of equipment after maintenance personnel perform servicing.

[0059] This invention provides a hybrid operation and maintenance method for airborne equipment. This method constructs a Gamma stochastic process model capable of characterizing nonlinear accelerated degradation, introduces Expected Life Extension (ELE) as a quantitative criterion for repair benefits, and establishes a long-term cost optimization framework that integrates detection, repair, protective replacement, and corrective replacement measures, including unplanned downtime losses. This enables collaborative decision-making for multiple types of operation and maintenance actions and automatic optimization configuration of key decision parameters. Specifically, see [link to relevant documentation]. Figure 1 As shown, the method includes the following steps:

[0060] S1. Based on the Gamma stochastic process, a degradation model for airborne equipment is constructed. The degradation model is a non-decreasing stochastic process used to characterize the evolution of equipment degradation over time.

[0061] S2. Using historical degradation sample data of the airborne equipment, the parameters of the degradation model are determined by parameter estimation method;

[0062] S3. Use airborne sensors to monitor the condition of the airborne equipment, obtain the current equipment degradation value, and calculate the average remaining life of the airborne equipment under the current equipment degradation value using the degradation model and its parameters.

[0063] S4. Construct a long-term unit time cost model, using the decision threshold as the optimization variable, and use an optimization algorithm to solve for the optimal parameter combination that minimizes the long-term unit time cost. Then, configure the optimal parameter combination into the operation and maintenance measures model.

[0064] S5. Based on the current equipment degradation value, the average remaining lifespan, and the historical operation and maintenance records of the airborne equipment, the operation and maintenance measure model and the decision threshold are used to determine the type of operation and maintenance measure and generate the corresponding decision instruction.

[0065] In one embodiment of step S1 above, the degradation of most airborne equipment is a macroscopic phenomenon caused by the accumulation of countless micro-damages within it. For example, during actual operation, the internal material of an airborne motor drive shaft continuously develops and expands micro-cracks, eventually leading to stress fatigue. Meanwhile, the degradation process of insulating materials at the microscopic level is caused by the gradual disintegration of the material under the influence of electric fields, heat, and other conditions, resulting in micro-cracks. Therefore, the degradation process of airborne equipment exhibits certain independent incremental, time-homogeneous, and non-decreasing characteristics, which can be characterized by a Gamma stochastic process.

[0066] In this invention, a random variable representing the degree of equipment degradation is defined, i.e., the equipment degradation value is X. When X = 0, it indicates that the equipment is brand new and has no degradation whatsoever; while when X = L, it indicates that the equipment degradation has reached its most severe level, at which point the equipment loses its existing function and malfunctions. L represents the maximum degradation value of the equipment. This invention does not limit the value of L and can define it according to the specific degree of degradation of the equipment. For example, if the length of the microcrack on the generator drive shaft is taken as the degree of equipment degradation, then the length of the microcrack at which it loses function can be used as the basis for the value of L. Therefore, this parameter is usually set based on engineering experience and the specific equipment.

[0067] Let X t Let be a random variable representing the degree of equipment degradation at time t. Then, the degradation increment of the equipment during the time interval t1 to t2 is... Δx follows a Gamma distribution, and its probability density function (which is the equipment degradation model used to quantify the equipment degradation process) is shown in the following equation:

[0068]

[0069] In the formula, The equipment degradation value at time t2. f is the equipment degradation value at time t1. α·Δt,β (Δx) represents the probability density corresponding to the minor arc increment Δx; Δt = t2 - t1 is the time interval length, i.e., the equipment degradation duration. Γ(·) is the Gamma function. Let Gamma be the function. α and β are the shape parameter and inverse scaling parameter of this distribution, respectively. From this, we can further deduce the probability of the time t taken for the airborne equipment to deteriorate by Δx:

[0070]

[0071] In the formula, As an incomplete Gamma function, further taking the partial derivative of Equation 2 with respect to time t yields the probability density function of this probability over the degradation time:

[0072]

[0073] In the formula, ψ(α)=Γ′(α) / Γ(α) is a double gamma function.

[0074] In a physical sense, the parameter α in the Gamma process characterizes the number of minor defects occurring in the equipment per unit time, while β characterizes the probability of each minor defect occurring. Since the degradation rate of most airborne equipment is not linear, and typically increases rapidly in the later stages of degradation, α can be considered as a variable α(x) representing the degree of equipment degradation x. This invention simplifies it into a piecewise function as shown in Equation 4:

[0075]

[0076] Therefore, the degradation model of airborne equipment consists of four parameters: shape parameters α1 and α2, degradation rate boundary point m, and inverse scale parameter β. These four parameters constitute the parameter set θ = {α1, α2, β, m}.

[0077] In one embodiment of step S2 above, the historical degradation sample data includes no less than 20 samples, each of which includes an initial degradation value, an initial time, a current device degradation value, and a current time; by constructing a likelihood function of the historical degradation sample data and maximizing the likelihood function, the parameters of the degradation model are solved.

[0078] Specifically, the parameters of the degradation model in S1 are set using the maximum likelihood method, employing no fewer than 20 samples, each containing the initial degradation value x of the equipment. b Initial time t b Current equipment degradation value X e and the current time t e Therefore, we can discuss different cases, and by combining equations 1 to 3 above, we can calculate the likelihood probability p of the i-th sample. i (θ):

[0079]

[0080] In the formula, || The curly braces {·} are indicator functions; the function value is 1 when the condition within the curly braces is met, and 0 otherwise.

[0081] Finally, the likelihood function of the sample set It can be given by the following equation 6:

[0082]

[0083] In the formula, n is the number of samples in the sample set. Subsequently, the parameters θ = {α1, α2, β, m} can be determined by maximizing equation 6. Based on the equipment degradation model and parameter determination method in steps S1 and S2, the degradation process of airborne equipment can be sampled, such as... Figure 2 As shown.

[0084] In one embodiment of step S3 above, when the degree of device degradation X at any time t... t When the value is ≥L, the equipment is considered to have failed at that time, and the degree of degradation will not increase further. Therefore, based on the degradation model of airborne equipment proposed in steps S1 and S2, the failure probability F of the airborne equipment at time u can be calculated using the following formula 7. m (u|x b},t b ;

[0085]

[0086] From the above formula, we can obtain that when u = t b The failure probability of the equipment is 0 when u→∞, and approaches 1 when u→∞.

[0087] On the other hand, based on the relationship between reliability and failure probability, the equipment reliability Rm(u|x) can be obtained as shown in Equation 8. b , t b )for:

[0088] R m (u|x b , t b )=1-F m (u|x b , t b (Equation 8);

[0089] The Mean Residual Life (MRL) of an equipment represents the expected time required for the equipment to go from its current state to failure. This parameter provides a strong basis for condition-based maintenance of the equipment. The expected value can be calculated at time t using the following equation (9): b The degree of degradation at any given time is x b The average remaining lifespan of airborne equipment is:

[0090]

[0091] Where, x b MRL(x) represents the current equipment degradation value. b (t) represents the current time. b The equipment degradation value is x b The average remaining lifetime at time t, where m is the dividing point of the degradation rate change, as shown in Equation 2 above. and These are the cumulative distribution functions of Gamma under the corresponding parameters. Let be the Gamma probability density function under the corresponding parameters, u and τ be the independent variables of the integral, and L be the preset fault threshold.

[0092] As can be seen from the above formula, the MRL of the device is only related to the initial degree of degradation, and is not related to the time when degradation begins. Figure 3 The MRL variation curves of the equipment degradation model under different initial degradation levels are given. The dotted line is the result of Monte Carlo sampling based on the degradation model, while the black solid line is the result of numerical calculation according to equation (9).

[0093] In one embodiment of step S4 above, it is necessary to first construct an operation and maintenance measure model, and then formulate a hybrid operation and maintenance decision rule (long-term unit time cost model) with memory. Assume that the airborne equipment starts to operate at time t=0, and follows the model deterioration shown in steps S1 and S2 until failure.

[0094] S41. Establishing an Operation and Maintenance Measures Model: In the condition-based operation and maintenance of airborne equipment, inspection, replacement, and repair are three common measures. They have different impacts on the equipment degradation process and also incur different costs. Since most equipment on an aircraft is a line-replaceable unit, these measures are considered to be completed instantaneously. As shown in Table 1 below, periodic inspection is a measure that collects equipment status variables through sensing technology. This measure does not affect the degree of equipment degradation, and the cost of each implementation is C. i .

[0095] Table 1. Various Operation and Maintenance Measures for Airborne Equipment

[0096]

[0097] Replacement is a perfect maintenance measure; regardless of the equipment's previous condition or any measures taken, the degree of degradation after replacement is zero. Replacement can be implemented either while the equipment is still operating normally or after a failure; the former is protective replacement, and the latter is corrective replacement. Corrective replacement is performed unplanned, and the equipment's degradation is more severe at this time, therefore it is more expensive than protective replacement. The cost of each protective and corrective replacement is C, respectively. prc and C crc Furthermore, due to various factors (such as equipment scheduling and negotiation), airborne equipment failures often prevent immediate replacement, resulting in unplanned aircraft grounding. To simplify the model, corrective replacement is assumed to occur during the next inspection after the equipment failure, during which time the unplanned grounding incurs additional overhead C per unit time. o .

[0098] Repair, on the other hand, is an imperfect, lightweight protective measure that restores equipment to a state better than before repair but worse than after the last intervention. Therefore, it has a lower cost compared to replacement. rpr To better analyze the impact of repair on the degree of equipment degradation, this section models the degree of degradation of the repaired equipment as a random variable, which can be derived from a truncated continuous distribution g. t Sampling is performed in (·), such as Figure 4 As shown. Let M i The time of this intervention (replacement or repair) and the degree of equipment deterioration since the last intervention. Deterioration level before this intervention The degree of degradation after repair It can be given by the following formula 10:

[0099]

[0100] The overhead costs of the above-mentioned operation and maintenance measures meet C. crc ≥C prc ≥C rpr ≥C i >0 and C o >0.

[0101] S42. Establishing a long-term unit time cost model: To obtain the optimal operation and maintenance system parameters and ensure that the long-term operation and maintenance cost of airborne equipment is minimized, this paper adopts a unit time cost C under an indefinite perspective. ∞ As an indicator for evaluating the long-term economic benefits of the operation and maintenance system, it is specifically shown in Equation 12 below:

[0102]

[0103] In the formula, C ∞ Unit time cost, N i (t), N prc (t), N crc (t), N rpr (t) represents the number of times the airborne equipment is inspected, protectively replaced, correctively replaced, and repaired within the time interval [0, t]; D(t) is the cumulative unplanned downtime of the airborne equipment due to malfunctions during the period [0, t]; C i C prc C crc C rpr C o These represent the weights for inspecting, protectively replacing, correctively replacing, and repairing airborne equipment. These parameters can be obtained through Monte Carlo sampling of the equipment degradation model, or approximated by calculating the unit time cost within a maintenance cycle. ∞ By solving equation 13, the optimal parameters of the operation and maintenance system can be found.

[0104]

[0105] In one embodiment of step S4 above, the decision threshold includes a repair determination threshold and a protective replacement threshold. The repair determination threshold is used to determine whether the expected life extension meets the repair conditions, and the protective replacement threshold is used to determine whether the equipment degradation state has reached the preventive replacement threshold.

[0106] In one embodiment of step S5 above, hybrid operation and maintenance decision rules are set: to coordinate various equipment maintenance measures, this invention constructs a parameterized decision architecture to implement condition-based operation and maintenance for airborne equipment. Through parameters... To formulate maintenance strategy rules. To adopt a hybrid operation and maintenance strategy for equipment, it is necessary to determine what intervention measures to take based on the equipment's history and current degradation status. This invention determines whether repair is worthwhile by predicting the lifespan extension after intervention. This invention proposes the concept of Expected Lifespan Extension (ELE), a parameter characterizing the degree of lifespan extension after equipment repair, which can be given by the following formula 11:

[0107]

[0108] This invention defines the time interval between two consecutive interventions as a maintenance cycle.

[0109] Specifically, the logic for generating decision instructions includes:

[0110] The difference between the current equipment degradation value and the random equipment degradation value after repair is calculated as the expected extended lifespan, and the expected extended lifespan is defined as the increment of the average remaining lifespan of the airborne equipment after the repair is performed.

[0111] When the expected lifespan extension is greater than the repair determination threshold, a decision instruction to perform repair is generated;

[0112] When the expected lifespan extension is less than or equal to the repair decision threshold, and the current equipment degradation value is greater than or equal to the protective replacement threshold, a decision instruction to perform protective replacement is generated.

[0113] When the current equipment degradation value is greater than or equal to a preset fault threshold, it is determined that the airborne equipment has failed, and a decision instruction to perform corrective replacement is generated.

[0114] More specifically, a maintenance cycle is defined as the time interval between two consecutive interventions. Considering that airborne equipment requires sufficient on-site testing after replacement or repair, therefore, during the cycle The first test time within is Let T be the time of the k-th detection within the i-th maintenance cycle. i，k Then the following rules apply:

[0115] 1. The degree of degradation before the k-th detection time within the i-th maintenance cycle. When a device malfunctions and requires immediate corrective replacement, the i-th maintenance cycle of the device ends, i.e., M. i =T i，k The degree of equipment degradation after replacement. The equipment then enters the next maintenance cycle.

[0116] 2. When At this point, although the equipment is still running, its deterioration is so severe that intervention is needed and the current maintenance cycle should be terminated, i.e., M. i =T i，k The appropriate intervention measures will depend on the degree of degradation of the equipment since the last intervention. Compared with the current state of degradation Further judgment should be made based on the combined information:

[0117] when At this point, repair is no longer sufficient to extend the equipment's lifespan, therefore protective replacement is necessary. The degree of equipment deterioration after replacement... The equipment then enters the next maintenance cycle;

[0118] when At this time, equipment repair offers advantages in terms of both economy and reliability, therefore repair should be implemented. The degree of equipment deterioration after repair. The equipment then enters the next maintenance cycle.

[0119] 3. When At that time, the equipment was still operating normally and required no intervention. This maintenance cycle continued, and the degree of equipment degradation remained unaffected.

[0120] 4. When At that time, the equipment is in the cycle The initial degradation level is low, and the equipment will not fail in a short period of time. Therefore, a periodic inspection strategy with a cycle of δ is adopted, hence T... i,k =T i,1 +(k-1)·δ.

[0121] 5. When At that time, the equipment is in the cycle The initial degradation level is high, and the probability of near-term failure is relatively high. Therefore, it will not be tested again during this cycle, and... The equipment is replaced directly, where μ is the safety margin, hence...

[0122] As can be seen from the above rules, there are 5 parameters in the operation and maintenance system of this invention. The values ​​of these parameters determine the characteristics of the operation and maintenance system. Considering practical realities, these parameters should meet the following requirements: And μ≥0. Figure 5 The diagram illustrates the evolution of equipment degradation when the above maintenance rules are adopted.

[0123] The hybrid operation and maintenance method for airborne equipment described in this invention has the following significant advantages compared to existing technologies:

[0124] 1. By adopting a nonlinear degradation model based on the Gamma stochastic process and setting the shape parameter as a piecewise function of the degradation state, the "accelerated degradation" characteristic of the equipment in the later stage of operation can be effectively characterized, significantly improving the accuracy of remaining life prediction and avoiding premature or late maintenance due to model mismatch.

[0125] 2. For the first time, four types of maintenance actions—detection, repair, protective replacement, and corrective replacement—are integrated under the same framework. The impact mechanism of each measure on the equipment's deterioration state is clarified (e.g., the state after repair follows a truncated distribution), forming a dynamic hybrid strategy that covers the entire life cycle of the equipment, breaking through the limitations of the traditional single maintenance mode.

[0126] 3. By defining "Expected Life Extension" (ELE) as the average remaining life increment brought about by the repair operation, and setting a repair decision threshold ELE, repair is only performed when ELE exceeds this threshold, ensuring that each repair is economically reasonable and avoiding inefficient or ineffective maintenance.

[0127] 4. The unplanned downtime loss term is explicitly included in the long-term unit time cost function to truly reflect the implicit costs of mission interruption and scheduling delay caused by failures in aviation scenarios, so that the optimization results can take into account both economy and mission assurance capability.

[0128] 5. Using decision thresholds (such as ELE and η) as optimization variables, the optimal combination is solved by combining Monte Carlo simulation and cost minimization algorithm, and automatically configured into the decision engine to form an adaptive closed loop of "evaluation-decision-optimization-re-decision", thus eliminating the dependence on human experience.

[0129] 6. By balancing the frequency of inspections, the timing of repairs, and the replacement strategy, the long-term unit time maintenance cost can be significantly reduced (simulations show a reduction of 15% to 30%) while ensuring equipment reliability. At the same time, it can reduce sudden failures and unplanned downtime events, and improve aircraft availability and mission completion rate.

[0130] In summary, this invention achieves an intelligent leap in airborne equipment operation and maintenance from "passive response" to "proactive prediction, precise decision-making, and autonomous optimization," combining technological advancement with engineering practicality.

[0131] Based on the same inventive concept, this invention also provides an airborne equipment hybrid operation and maintenance system, as described in the following embodiments. Since the principle of the airborne equipment hybrid operation and maintenance system in solving the problem is similar to the airborne equipment hybrid operation and maintenance method disclosed in the above embodiments, the implementation of the airborne equipment hybrid operation and maintenance system can refer to the implementation of the airborne equipment hybrid operation and maintenance method, and repeated details will not be elaborated further. As used below, the terms "unit" or "module" can refer to a combination of software and / or hardware that implements a predetermined function. Although the apparatus described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0132] Figure 6 This is a structural block diagram of an airborne equipment hybrid operation and maintenance system disclosed in an embodiment of the present invention, such as... Figure 6 As shown, the system includes a degradation modeling module 601, a parameter estimation module 602, a reliability assessment module 603, a decision generation module 604, and a strategy optimization module 605. The structure is described below.

[0133] Among them, the degradation modeling module 601 is used to construct a degradation model of airborne equipment based on the Gamma stochastic process. The degradation model is a non-decreasing stochastic process used to characterize the evolution law of equipment degradation degree over time.

[0134] The parameter estimation module 602 is used to determine the parameters of the degradation model by using the historical degradation sample data of the airborne equipment and employing a parameter estimation method.

[0135] The reliability assessment module 603 is used to monitor the condition of the airborne equipment using airborne sensors, obtain the current equipment degradation value, and calculate the average remaining life of the airborne equipment under the current equipment degradation value through the degradation model and its parameters.

[0136] The decision generation module 604 is used to construct a long-term unit time cost model, using the decision threshold as the optimization variable, and employing an optimization algorithm to solve for the optimal parameter combination that minimizes the long-term unit time cost, and then configuring the optimal parameter combination into the operation and maintenance measures model.

[0137] The strategy optimization module 605 is used to determine the type of maintenance measures and generate corresponding decision instructions based on the current equipment degradation value, the average remaining lifespan, and the historical maintenance records of the airborne equipment, using the maintenance measure model and the decision threshold.

[0138] In this embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements any of the above-described hybrid operation and maintenance methods for airborne equipment.

[0139] Specifically, the computer device can be a computer terminal, a server, or a similar computing device.

[0140] In this embodiment, a computer-readable storage medium is provided, which stores a computer program that executes any of the above-described hybrid operation and maintenance methods for airborne equipment.

[0141] Specifically, computer-readable storage media, including both permanent and non-permanent, removable and non-removable media, can store information using any method or technology. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer-readable storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable storage media does not include transient media, such as modulated data signals and carrier waves.

[0142] Obviously, those skilled in the art should understand that the modules or steps of the above-described embodiments of the present invention can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. Optionally, they can be implemented using computer-executable program code, thereby storing them in a storage device for execution by a computing device. In some cases, the steps shown or described can be performed in a different order than those presented here, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, the embodiments of the present invention are not limited to any particular hardware and software combination.

[0143] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, various modifications and variations can be made to the embodiments of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A hybrid operation and maintenance method for airborne equipment, characterized in that, include: Based on the Gamma stochastic process, a degradation model for airborne equipment is constructed. The degradation model is a non-decreasing stochastic process used to characterize the evolution of equipment degradation over time. The parameters of the degradation model are determined using a parameter estimation method based on historical degradation sample data of the airborne equipment. Airborne sensors are used to monitor the condition of the airborne equipment to obtain the current equipment degradation value, and the average remaining life of the airborne equipment under the current equipment degradation value is calculated using the degradation model and its parameters. A long-term unit time cost model is constructed, with the decision threshold as the optimization variable. An optimization algorithm is used to solve for the optimal parameter combination that minimizes the long-term unit time cost. The optimal parameter combination is then configured into the operation and maintenance measures model. Based on the current equipment degradation value, the average remaining lifespan, and the historical maintenance records of the airborne equipment, the maintenance measure model and the decision threshold are used to determine the maintenance measure type and generate corresponding decision instructions.

2. The hybrid operation and maintenance method for airborne equipment according to claim 1, characterized in that, The degradation increment of the airborne equipment within the time interval [t1-t2] It follows a Gamma distribution, and its probability density function is: in, The equipment degradation value at time t2. f is the equipment degradation value at time t1. α·Δt，β (Δc) is the probability density corresponding to the degradation increment Δx; Γ(·) is the Gamma function; α and β are the shape parameter and inverse scaling parameter of the Gamma distribution, respectively; Δt=t2-t1 is the time interval length.

3. The hybrid operation and maintenance method for airborne equipment according to claim 1, characterized in that, The historical degradation sample data includes no fewer than 20 samples, and each sample includes an initial degradation value, an initial time, a current device degradation value, and a current time. The parameters of the degradation model are solved by constructing the likelihood function of the historical deterioration sample data and maximizing the likelihood function.

4. The hybrid operation and maintenance method for airborne equipment according to claim 1, characterized in that, The formula for calculating the average remaining lifespan is: Where, x b MRL(x) represents the current equipment degradation value. b (t) represents the current time. b The equipment degradation value is x b The mean remaining lifetime at time m is the cutoff point for the rate of degradation. and These are the cumulative distribution functions of Gamma under the corresponding parameters. Let τ be the probability density function of Gamma under the corresponding parameters, u and τ be the independent variables of the integral, and L be the preset fault threshold.

5. The hybrid operation and maintenance method for airborne equipment according to claim 1, characterized in that, The expression for the long-run unit time cost model is: Among them, C ∞ Unit time cost, N i (t), N prc (t), N crc (t), N rpr (t) represents the number of times the airborne equipment is inspected, protectively replaced, correctively replaced, and repaired within the time interval [0, t]; D(t) is the cumulative unplanned downtime of the airborne equipment due to malfunctions during the period [0, t]; C i C prc C crc C rpr C o The weights for inspecting, protectively replacing, correctively replacing, and repairing airborne equipment are respectively assigned.

6. The hybrid operation and maintenance method for airborne equipment according to claim 1, characterized in that, The decision thresholds include a repair determination threshold and a protective replacement threshold. The repair determination threshold is used to determine whether the expected life extension meets the repair conditions, and the protective replacement threshold is used to determine whether the equipment degradation state has reached the preventive replacement threshold.

7. The hybrid operation and maintenance method for airborne equipment according to claim 6, characterized in that, The logic for generating decision instructions includes: The difference between the current equipment degradation value and the random equipment degradation value after repair is calculated as the expected extended lifespan, and the expected extended lifespan is defined as the increment of the average remaining lifespan of the airborne equipment after the repair is performed. When the expected lifespan extension is greater than the repair determination threshold, a decision instruction to perform repair is generated; When the expected lifespan extension is less than or equal to the repair decision threshold, and the current equipment degradation value is greater than or equal to the protective replacement threshold, a decision instruction to perform protective replacement is generated. When the current equipment degradation value is greater than or equal to a preset fault threshold, it is determined that the airborne equipment has failed, and a decision instruction to perform corrective replacement is generated.

8. A hybrid operation and maintenance system for airborne equipment, characterized in that, include: The degradation modeling module is used to construct a degradation model for airborne equipment based on a Gamma stochastic process. The degradation model is a non-decreasing stochastic process used to characterize the evolution of equipment degradation over time. The parameter estimation module is used to determine the parameters of the degradation model by using the historical degradation sample data of the airborne equipment and employing parameter estimation methods. The reliability assessment module is used to monitor the condition of the airborne equipment using airborne sensors, obtain the current equipment degradation value, and calculate the average remaining life of the airborne equipment under the current equipment degradation value using the degradation model and its parameters. The decision generation module is used to construct a long-term unit time cost model. Using the decision threshold as the optimization variable, it uses an optimization algorithm to solve for the optimal parameter combination that minimizes the long-term unit time cost, and then configures the optimal parameter combination into the operation and maintenance measures model. The strategy optimization module is used to determine the type of maintenance measures and generate corresponding decision instructions based on the current equipment degradation value, the average remaining lifespan, and the historical maintenance records of the airborne equipment, using the maintenance measure model and the decision threshold.

9. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the hybrid operation and maintenance method for airborne equipment as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that executes the hybrid operation and maintenance method for airborne equipment as described in any one of claims 1 to 7.

Images