Equipment health state monitoring and quality control measure decision-making method and system

Abstract

The invention discloses an equipment health state monitoring and quality control measure decision-making method and a system with the method, and the method comprises the steps: determining different health states describing equipment, and determining state monitoring corresponding to the health states and quality control measures corresponding to the health states according to the different health states; according to historical data, obtaining transfer rates of different health states of the equipment, and determining different health states, state monitoring corresponding to the health states and expected benefits of quality control measures corresponding to the health states; determining the state frequency of the Markov process-based device staying in different health states and the average duration of the Markov process-based device in different health states; determining the available time of the equipment according to the average duration, and determining the optimal state monitoring frequency; and determining different health states of the equipment according to the average duration, and determining an optimal quality control measure according to the sum of expected benefits of state monitoring and quality control measures.

Description

Technical Field

[0001] The present invention relates to the technical field of equipment health assessment, and in particular to a method and system for equipment health status monitoring and quality control measure decision-making. Background Art

[0002] Given that the health status of operating equipment can only be diagnosed periodically, failure risk prediction for equipment cannot immediately provide the current health status of the equipment. Instead, the likely distribution of the equipment's current health status must be predicted based on its health status over a period of time. Traditional models only consider the impact of real-time operating status on equipment failure rates. By incorporating a Markov process to predict equipment health status, we can further quantitatively analyze and select optimal quality control measures.

[0003] Therefore, a technology is needed to solve the problem of equipment health status monitoring and optimization of quality control measures. Summary of the Invention

[0004] The present invention aims to address at least one of the technical problems existing in the prior art. To this end, it proposes a fusion method for dynamic measurement uncertainty assessment. This method addresses the high data requirements and limited functionality of previous methods, thereby better adapting to diverse needs and achieving more accurate uncertainty assessment.

[0005] The present invention also proposes a system having the above-mentioned fusion method for dynamic measurement uncertainty evaluation.

[0006] According to a first aspect of the present invention, a method for monitoring equipment health and deciding on quality control measures includes:

[0007] Obtain different health states of the device, and determine, based on the different health states, status monitoring and quality control measures corresponding to the health states;

[0008] Based on historical data, obtain the transfer rate of different health states of the device, the expected benefits of different health states of the device, the expected benefits of status monitoring corresponding to the health states, and the expected benefits of quality control measures corresponding to the health states;

[0009] determining a state frequency of the device staying in the different health states based on a Markov process and calculating an average duration of the device in different health states based on the state frequency;

[0010] Determine the available time of the device according to the average duration of the different health states, establish a condition monitoring frequency model with the longest available time of the device as the goal, and determine the optimal condition monitoring frequency;

[0011] According to the average duration of the different health states, the expected sum of the different health states of the equipment, the state monitoring corresponding to the health states, and the expected benefits of the quality control measures corresponding to the health states are determined. A quality control measure model is established with the highest expected sum of the expected benefits of the equipment as the goal, and the optimal quality control measure is determined.

[0012] The method for equipment health status monitoring and quality control measure decision-making according to an embodiment of the present invention has at least the following beneficial effects: the method for equipment health status monitoring and quality control measure decision-making provided by the present invention determines the status monitoring corresponding to the health status and the quality control measures corresponding to the health status according to different health statuses; obtains the transfer rate of different health statuses of the equipment according to historical data, and determines the expected benefits of different health statuses, status monitoring corresponding to the health status, and quality control measures corresponding to the health status; determines the state frequency of the equipment staying in different health statuses and the average duration of the equipment staying in different health statuses based on the Markov process; determines the available time of the equipment according to the average duration, and determines the optimal state monitoring frequency; determines the sum of the expected benefits of different health statuses, status monitoring, and quality control measures of the equipment according to the average duration, and determines the optimal quality control measures. This solves the problem of poor immediacy in equipment health status monitoring and quality control measures in traditional methods.

[0013] According to some embodiments of the present invention, the expected benefits of the different health states of the device are operating benefits obtained by maintaining the health states;

[0014] The expected benefit of the state monitoring corresponding to the health state is the funds for implementing the state monitoring;

[0015] The expected benefit of the quality control measures corresponding to the health status is the funds for implementing the maintenance decision.

[0016] According to some embodiments of the present invention, the step of determining the state frequency of the device staying in the different health states based on the Markov process and calculating the average duration of the device in the different health states based on the state frequency includes:

[0017] The health process of the device is described according to a Markov random process model. The limit state of the health state of the device after n steps of transfer is the stable state of the health state of the device. The probability of the stable state after entering the healthy state is a constant, and the probability of the stable state is independent of the initial state of the device.

[0018] The linear differential equations of the Markov stochastic process are:

[0019]

[0020] Among them, λ ij is the transfer rate, P(t) is the Markov general equation, and t is the time;

[0021] The stationary state probability is obtained by solving the following linear equations:

[0022]

[0023] When the device health process reaches the stable state, the average number of times the device stays in the health state i per unit time is the state frequency f of the device in state i. i , the duration T of state i i It refers to the average duration of the equipment staying in state i when the health process reaches a stable state, f ij is the frequency of j transitions to state i, where

[0024]

[0025] According to some embodiments of the present invention, the steps of determining the available time of the device based on the average duration of the different health states, establishing a condition monitoring frequency model with the longest available time of the device as the goal, and determining the optimal condition monitoring frequency include:

[0026] The objective function of the condition monitoring frequency model established with the goal of maximizing the available time of the equipment is max{B}, where B is a function of the monitoring frequency γ, B=f(γ), f(γ) is a functional relationship between the equipment detection frequency and the available time of the equipment, the monitoring frequency is a variable, the available time is a dependent variable, and the optimal monitoring frequency γ satisfies:

[0027] γ min ≤γ≤γ max

[0028] where γ max , γ min are the maximum and minimum values ​​of the monitoring frequency respectively.

[0029] According to some embodiments of the present invention, the step of determining the sum of expected benefits of the different health states of the device, the state monitoring corresponding to the health states, and the quality control measures corresponding to the health states based on the average durations of the different health states, and determining the optimal quality control measure with the goal of maximizing the sum of expected benefits of the device includes:

[0030] With the goal of maximizing the total expected benefits of the equipment, the objective function of the optimal quality control measures model is determined to be: max{G}, where G is the sum of the expected benefits of the different health states, the state monitoring corresponding to the health states, and the quality control measures corresponding to the health states during the entire life cycle of the equipment.

[0031] According to some embodiments of the present invention, the time for transitioning between the different health states of the device follows an exponential distribution, and the probability of transitioning between the different health states is constant.

[0032] According to a second aspect of the present invention, a system for equipment status monitoring and quality control measures includes:

[0033] An initialization unit, configured to obtain different health states describing the device, and determine, based on the different health states, state monitoring and quality control measures corresponding to the health states;

[0034] an acquisition unit, configured to acquire, based on historical data, the transition rates of different health states of the device, the expected benefits of different health states of the device, the expected benefits of status monitoring corresponding to the health states, and the expected benefits of the quality control measures corresponding to the health states;

[0035] a first calculation unit, configured to determine a state frequency of the device staying in the different health states based on a Markov process and calculate an average duration of the device in different health states based on the state frequency;

[0036] a second calculation unit, configured to determine the available time of the device according to the average duration of the different health states, establish a condition monitoring frequency model with the longest available time of the device as the goal, and determine the optimal condition monitoring frequency;

[0037] The third calculation unit is used to determine the different health states of the equipment, the expected sum of the state monitoring corresponding to the health states, and the quality control measures corresponding to the health states based on the average duration of the different health states, and determine the optimal quality control measures with the goal of maximizing the expected sum of the expected benefits of the equipment.

[0038] According to some embodiments of the present invention, the expected benefits of the different health states of the device are operating benefits obtained by maintaining the health states;

[0039] The expected benefit of the state monitoring corresponding to the health state is the funds for implementing the state monitoring;

[0040] The expected benefit of the quality control measures corresponding to the health status is the funds for implementing the maintenance decision.

[0041] According to some embodiments of the present invention, the first computing unit further includes:

[0042] The health process of the device is described according to a Markov random process model. The limit state of the health state of the device after n steps is the stable state of the health state of the device. The probability of the stable state after entering the healthy state is a constant, and the probability of the stable state is independent of the initial state of the device.

[0043] The linear differential equations of the Markov stochastic process are:

[0044]

[0045] Among them, λ ij is the transfer rate, P(t) is the Markov general equation, and t is the time;

[0046] The stationary state probability is obtained by solving the following linear equations:

[0047]

[0048] When the device health process reaches the stable state, the average number of times the device stays in the health state i per unit time is the state frequency f of the device in state i. i , the duration T of state i i It refers to the average duration of the equipment staying in state i when the health process reaches a stable state, f ij is the frequency of j transitions to state i, where

[0049]

[0050] According to some embodiments of the present invention, the second computing unit further includes:

[0051] The objective function of the condition monitoring frequency model established with the goal of maximizing the available time of the equipment is max{B}, where B is a function of the monitoring frequency γ, B=f(γ), f(γ) is a functional relationship between the equipment detection frequency and the available time of the equipment, the monitoring frequency is a variable, the available time is a dependent variable, and the optimal monitoring frequency γ satisfies:

[0052] γ min ≤γ≤γ max

[0053] where γ max , γ min are the maximum and minimum values ​​of the monitoring frequency respectively.

[0054] According to some embodiments of the present invention, the third computing unit further includes:

[0055] With the goal of maximizing the total expected benefits of the equipment, the objective function of the optimal quality control measures model is determined to be: max{G}, where G is the sum of the expected benefits of the different health states, the state monitoring corresponding to the health states, and the quality control measures corresponding to the health states during the entire life cycle of the equipment.

[0056] According to some embodiments of the present invention, the time for transitioning between the different health states of the device follows an exponential distribution, and the probability of transitioning between the different health states is constant.

[0057] Additional aspects and advantages of the present invention will be set forth in part in the description which follows and, in part, will be obvious from the description which follows, or may be learned by practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] The above and / or additional aspects and advantages of the present invention will become apparent and readily understood from the following description of the embodiments with reference to the accompanying drawings, in which:

[0059] Figure 1 A flow chart of a method for equipment status monitoring and maintenance decision-making according to an embodiment of the present invention;

[0060] Figure 2 for Figure 1 The equipment state transition model diagram in the equipment state monitoring and maintenance decision-making method is shown;

[0061] Figure 3 This is a system structure diagram of equipment status monitoring and maintenance decision-making in an embodiment of the present invention. DETAILED DESCRIPTION

[0062] The following describes embodiments of the present invention in detail. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended only to explain the present invention and are not to be construed as limiting the present invention.

[0063] In the description of the present invention, it should be understood that descriptions involving orientations, such as up, down, front, back, left, right, etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings. They are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation. Therefore, they cannot be understood as limitations on the present invention.

[0064] In the description of the present invention, "several" means one or more, "many" means more than two, "greater than," "less than," and "exceed" are understood to exclude the number itself, while "above," "below," and "within" are understood to include the number itself. The use of "first" and "second" in the description is solely for the purpose of distinguishing technical features and should not be construed as indicating or implying relative importance, implicitly specifying the number of the indicated technical features, or implicitly specifying the order of the indicated technical features.

[0065] In the description of the present invention, unless otherwise clearly defined, terms such as setting, installing, and connecting should be understood in a broad sense, and technicians in the relevant technical field can reasonably determine the specific meanings of the above terms in the present invention based on the specific content of the technical solution.

[0066] Example 1

[0067] The embodiment of the present invention provides a method for equipment status monitoring and maintenance decision-making based on Markov process. Figure 1 As shown, this embodiment uses equipment as the object and proposes a model and solution method for equipment status monitoring and quality control measures. Guided by the concepts of equipment lifecycle management, status monitoring, quality control measures, and related concepts, a device status transition model based on a Markov random process is proposed. The relevant indicator parameters are calculated based on the Markov process equation, enabling quantitative analysis of equipment reliability and demonstrating strong operability.

[0068] Specifically, the above-mentioned equipment status monitoring and quality control measures include:

[0069] Step S100: Acquire different health states describing the device, and determine, based on the different health states, state monitoring corresponding to the health state and quality control measures corresponding to the health state.

[0070] In reliability analysis, the health process of a device can be represented as the continuous loss of health until failure occurs. The embodiments of the present invention describe the different stages of the device health process as Health State 1, Health State 2, and Health State 3. Without maintenance, the device will progress from Health State 1 to Health State 3 and finally to a failure state. After a device failure, it can be restored to Health State 1 through replacement or repair. Each health state has corresponding status monitoring, and maintenance personnel will make different maintenance decisions based on the status monitoring results, that is, adopt different maintenance measures. After maintenance, the device will also return to a different state.

[0071] Step S200: Based on historical data, obtain the transfer rate of different health states of the device, the expected benefits of different health states of the device, the expected benefits of status monitoring corresponding to the health state, and the expected benefits of quality control measures corresponding to the health state.

[0072] The expected benefits of different health states of equipment are the operating benefits obtained by maintaining the healthy state; the expected benefits of condition monitoring corresponding to the healthy state are the funds for implementing condition monitoring; and the expected benefits of quality control measures corresponding to the healthy state are the funds for implementing maintenance decisions.

[0073] The transition rate between different equipment health states is derived from historical statistical data and is expressed in units of per year. The expected benefit of each health state refers to the operating revenue that can be achieved by maintaining the equipment in that health state. The expected benefit of health monitoring refers to the funds spent on implementing health monitoring, and the expected benefit of maintenance refers to the funds spent on implementing different maintenance methods.

[0074] Step S300: Determine the state frequency of the device staying in the different health states based on a Markov process and calculate the average duration of the device in different health states based on the state frequency.

[0075] Preferably, determining the state frequency of the device staying in different health states and the average duration of the device staying in different health states based on the Markov process includes:

[0076] The health process of the equipment is described by the Markov random process model. The limit state of the equipment's health state after n steps is the stable state of the equipment's health state. The probability of the stable state after entering the healthy state is a constant, and the probability of the stable state is independent of the initial state of the equipment.

[0077] The linear differential equations of the Markov stochastic process are:

[0078]

[0079] Among them, λ ij is the transfer rate, P(t) is the Markov general equation, and t is the time;

[0080] The stationary state probabilities are obtained by solving the following system of linear equations:

[0081]

[0082] When the equipment health process reaches a stable state, the average number of times it stays in health state i per unit time is the state frequency f of the equipment in state i i , the duration T of state i i It refers to the average duration of the equipment staying in state i when the health process reaches a stable state, f ij is the frequency of j transitions to state i, where:

[0083]

[0084] Step S400: Determine the available time of the device based on the average duration of different health states, establish a condition monitoring frequency model with the longest available time of the device as the goal, and determine the optimal condition monitoring frequency. Preferably, determining the available time of the device based on the average duration of different health states, establishing a condition monitoring frequency model with the longest available time of the device as the goal, and determining the optimal condition monitoring frequency includes:

[0085] The objective function of the condition monitoring frequency model established with the goal of maximizing the equipment availability is max{B}, where B is a function of the monitoring frequency γ, B = f(γ), and f(γ) is a functional relationship between the equipment detection frequency and the equipment availability. The monitoring frequency is a variable, and the availability time is a dependent variable. The optimal monitoring frequency γ satisfies:

[0086] γ min ≤γ≤γ max , where γ max , γ min are the maximum and minimum values ​​of the monitoring frequency respectively.

[0087] Step S500: Determine the different health states of the equipment, the state monitoring corresponding to the health states, and the sum of the expected benefits of the quality control measures corresponding to the health states based on the average duration of the different health states, establish a quality control measure model with the highest expected sum of the benefits of the equipment as the goal, and determine the optimal quality control measure.

[0088] Taking the maximum expected total benefit of the equipment as the goal, the objective function of the optimal quality control measures model is determined as: max{G}, where G is the sum of the expected benefits of the equipment in different health states, the condition monitoring corresponding to the health state, and the quality control measures corresponding to the health state throughout its life cycle.

[0089] The process of solving the function includes:

[0090] S501. Given an initial decision for iteration, in order to reduce the number of iterations and simplify the iteration process, the embodiment of the present invention gives an initial maintenance strategy based on the principle of maximizing the expected benefit of each health state.

[0091] S502. Change the maintenance strategy and calculate the expected benefits over the entire life cycle.

[0092] S503: Determine whether the expected benefit of the equipment health status process over its entire life cycle after changing the maintenance strategy is maximized. If not, repeat S502. If the strategies are identical during the iteration, the current strategy is the optimal maintenance strategy, and the iteration can be stopped. The maintenance strategy obtained at this point is the optimal strategy for equipment health maintenance.

[0093] Example 2

[0094] For the method proposed in the first embodiment, another embodiment of the present application provides a specific example.

[0095] This embodiment equates the health status process of the device to a random process, establishing Figure 2 The device health process state transition model shown in Figure 1 includes the different health stages and fault states of the device health process, as well as health status monitoring and maintenance decisions throughout the device lifecycle. Assuming that the device can transition from its current health state to other states, and that the transition time between health states follows an exponential distribution—that is, the probability of health state transition is constant—then the device's next health state is solely dependent on the current state. The exponential distribution is a continuous probability distribution in probability theory and statistics that can be used to represent the time intervals between independent random events. One of its key characteristics is its memorylessness.

[0096] For example, the state transition probability from health state 2 to health state 3 is constant, and health state 3 is only related to health state 2 and has nothing to do with health state 1.

[0097] Figure 2 The health process of a device is represented by three separate health states. Eventually, the device enters a fault state, which can be replaced or repaired to restore it to its original healthy state. Each health state corresponds to a conditional monitor, which determines a maintenance strategy. After maintenance, the device can be restored to its previous healthy state.

[0098] Healthy state 2 corresponds to state monitoring 2. After monitoring, the maintenance personnel decide to adopt maintenance means 2. Through the implementation of maintenance, the state of the equipment is restored from healthy state 2 to healthy state 1.

[0099] λ n , δ n , γ n and μ n Represent the transition probability between different states, where λ n It refers to the transition probability of the device from healthy state n to healthy state n+1.

[0100] δ n It refers to the transition probability of implementing maintenance measure n after the equipment is monitored for condition n.

[0101] γ n It refers to the transition probability of implementing state monitoring n for the health state n of the equipment.

[0102] μ n It refers to the transition probability that the equipment returns to a healthy state n-1 after implementing maintenance measures n on the equipment.

[0103] Since different maintenance decisions will be made after status monitoring of equipment in different health states, and different maintenance measures will have different impacts on the economic efficiency of equipment operation, the expected benefits for different states are given to describe the economic efficiency of equipment maintenance.

[0104] Taking Health State 2 as an example, if Condition Monitoring 2 isn't implemented while the device is in Health State 2, maintenance personnel won't be able to detect that the device has reached Health State 2. Consequently, the costs associated with implementing different Condition Monitoring methods will vary. Similarly, if Condition Monitoring 2 is implemented and the device is found to be in Health State 2, but maintenance personnel don't decide to implement Maintenance Method 2, the device won't be able to return to Health State 1. Consequently, the costs associated with different maintenance methods will also vary. Ultimately, this will lead to different expected returns.

[0105] After establishing a state transition model for the equipment health process and determining the expected benefits for each state and the transition rates between health states, the probability of the equipment health process reaching a steady state and the average duration of each health state can be calculated. The steady state probability indicates that once the equipment health process enters a steady state, the transition probabilities of each state remain unchanged even if another state transition occurs.

[0106] After obtaining the above parameters, namely the expected benefit of each health state, the average duration of each health state, and the health state transition probability, an optimization model for the equipment routine condition monitoring frequency can be established. With the longest equipment available time as the objective equation, an optimization method is applied to find the optimal routine condition monitoring frequency. After determining the routine inspection frequency, an equipment condition maintenance optimization decision model can be established and an iterative method can be applied to obtain the optimal maintenance strategy. The steps are as follows:

[0107] (1) First, an initial decision for iteration is given. To reduce the number of iterations and simplify the iteration process, the embodiment of the present invention gives an initial maintenance strategy based on the principle of maximizing the expected benefit of each health state;

[0108] (2) Change the maintenance strategy and calculate the expected benefits over the entire life cycle;

[0109] (3) Determine whether the expected benefit of the equipment health process over the entire life cycle after changing the maintenance strategy is maximized. If not, repeat step (2). If the strategies before and after the iteration are the same, it indicates that the current strategy is the optimal maintenance strategy and the iteration can be stopped. The maintenance strategy obtained at this time is the optimal strategy for equipment condition maintenance.

[0110] The equipment condition maintenance optimization decision-making method provided by the present invention uses Markov processes to describe the health process of equipment in the context of full life cycle management of power equipment, which can more accurately quantify the reliability of the equipment. When optimizing the maintenance strategy, the reliability and economy of the equipment operation are comprehensively considered, which can achieve better maintenance results.

[0111] Example 3:

[0112] Another embodiment of the present invention provides a system structure diagram for equipment status monitoring and maintenance decision-making. Figure 3 As shown, the system 300 includes:

[0113] Initialization unit 301 is used to obtain different health states of the device and determine the state monitoring and quality control measures corresponding to the health state according to the different health states;

[0114] An acquisition unit 302 is configured to acquire, based on historical data, transition rates of different health states of the device, expected benefits of different health states of the device, expected benefits of status monitoring corresponding to the health states, and expected benefits of quality control measures corresponding to the health states;

[0115] A first calculation unit 303 is configured to determine a state frequency of the device staying in the different health states based on a Markov process and calculate an average duration of the device in different health states based on the state frequency;

[0116] The second calculation unit 304 is configured to determine the available time of the device according to the average duration of the different health states, establish a condition monitoring frequency model with the longest available time of the device as the goal, and determine the optimal condition monitoring frequency;

[0117] The third calculation unit 305 is used to determine the different health states of the equipment, the expected sum of the state monitoring corresponding to the health states, and the quality control measures corresponding to the health states based on the average duration of the different health states, and determine the optimal quality control measures with the goal of maximizing the expected sum of the benefits of the equipment.

[0118] Preferably, the expected benefits of the different health states of the equipment are the operating benefits obtained by maintaining the health states;

[0119] The expected benefit of the condition monitoring corresponding to the health state is the funds for implementing the condition monitoring;

[0120] The expected benefit of the quality control measures corresponding to the health state is the funds for implementing the maintenance decision.

[0121] Preferably, the first calculation unit 303 further includes:

[0122] The health process of the device is described according to a Markov random process model. The limit state of the health state of the device after n steps is the stable state of the health state of the device. The probability of the stable state after entering the healthy state is a constant, and the probability of the stable state is independent of the initial state of the device.

[0123] The linear differential equations of the Markov stochastic process are:

[0124]

[0125] Among them, λ ij is the transfer rate, P(t) is the Markov general equation, and t is the time;

[0126] The stationary state probability is obtained by solving the following linear equations:

[0127]

[0128] When the device health process reaches the stable state, the average number of times the device stays in the health state i per unit time is the state frequency f of the device in state i. i , the duration T of state i i It refers to the average duration of the equipment staying in state i when the health process reaches a stable state, f ij is the frequency of j transitions to state i, where

[0129]

[0130] Preferably, the second calculation unit 304 further includes:

[0131] The objective function of the condition monitoring frequency model established with the goal of maximizing the available time of the equipment is max{B}, where B is a function of the monitoring frequency γ, B=f(γ), f(γ) is a functional relationship between the equipment detection frequency and the available time of the equipment, the monitoring frequency is a variable, the available time is a dependent variable, and the optimal monitoring frequency γ satisfies:

[0132] γ min ≤γ≤γ max

[0133] where γ max , γ min are the maximum and minimum values ​​of the monitoring frequency respectively.

[0134] Preferably, the third calculation unit 305 further includes:

[0135] With the goal of maximizing the total expected benefits of the equipment, the objective function of the optimal quality control measures model is determined to be: max{G}, where G is the sum of the expected benefits of the different health states, the state monitoring corresponding to the health states, and the quality control measures corresponding to the health states during the entire life cycle of the equipment.

[0136] Preferably, the time for transitioning between the different health states of the device follows an exponential distribution, and the probability of transitioning between the different health states is constant.

[0137] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, i.e., they may be located in one place or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of this embodiment.

[0138] Those skilled in the art will appreciate that all or some of the steps and systems in the method disclosed above can be implemented as software, firmware, hardware, and appropriate combinations thereof. Some physical components or all physical components can be implemented as software executed by a processor, such as a central processing unit, a digital signal processor, or a microprocessor, or implemented as hardware, or implemented as an integrated circuit, such as an application-specific integrated circuit. Such software can be distributed on a computer-readable medium, and the computer-readable medium can include computer storage media (or non-transitory media) and communication media (or temporary media). As known to those skilled in the art, the term computer storage media is included in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data) and is volatile and non-volatile, removable, and non-removable. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory, or other memory technology, CD-ROM, digital versatile disks (DVD), or other optical disk storage, magnetic cassettes, magnetic tapes, disk storage, or other magnetic storage devices, or any other medium that can be used to store desired information and can be accessed by a computer. Furthermore, as is well known to those skilled in the art, communication media typically embodies computer-readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transport mechanism, and may include any information delivery media.

[0139] The above is a specific description of the preferred implementation of the present application, but the present application is not limited to the above implementation mode. Technical personnel familiar with the field can also make various equivalent modifications or substitutions without violating the spirit of the present application. These equivalent modifications or substitutions are all included in the scope defined by the claims of the present application.

Claims

1. A method for monitoring equipment health and determining quality control measures, the method comprising: Obtain different health states of the device, and determine, based on the different health states, status monitoring and quality control measures corresponding to the health states; Based on historical data, obtain the transfer rate of different health states of the device, the expected benefits of different health states of the device, the expected benefits of status monitoring corresponding to the health states, and the expected benefits of quality control measures corresponding to the health states; determining a state frequency of the device staying in the different health states based on a Markov process and calculating an average duration of the device in different health states based on the state frequency; Determine the available time of the device according to the average duration of the different health states, establish a condition monitoring frequency model with the longest available time of the device as the goal, and determine the optimal condition monitoring frequency; According to the average duration of the different health states, the expected sum of the different health states of the equipment, the state monitoring corresponding to the health states, and the expected benefits of the quality control measures corresponding to the health states are determined. A quality control measure model is established with the highest expected sum of the expected benefits of the equipment as the goal, and the optimal quality control measure is determined.

2. The method according to claim 1, wherein the expected benefits of the different health states of the equipment are the operating benefits obtained by maintaining the health states; The expected benefit of the state monitoring corresponding to the health state is the funds for implementing the state monitoring; The expected benefit of the quality control measures corresponding to the health status is the funds for implementing the maintenance decision.

3. The method according to claim 1 , wherein determining the state frequencies of the device staying in the different health states based on a Markov process and calculating the average duration of the device staying in the different health states based on the state frequencies comprises: The health process of the device is described according to a Markov random process model. The limit state of the health state of the device after n steps of transfer is the stable state of the health state of the device. The probability of the stable state after entering the healthy state is a constant, and the probability of the stable state is independent of the initial state of the device. The linear differential equations of the Markov stochastic process are: Among them, λ ij is the transfer rate, P(t) is the Markov general equation, and t is the time; The stationary state probability is obtained by solving the following linear equations: When the device health process reaches the stable state, the average number of times the device stays in the health state i per unit time is the state frequency f of the device in state i. i , the duration T of state i i It refers to the average duration of the equipment staying in state i when the health process reaches a stable state, f ij is the frequency of j transitions to state i, where 4. The method according to claim 1, wherein the steps of determining the available time of the device based on the average duration of the different health states, establishing a condition monitoring frequency model with the longest available time of the device as the goal, and determining the optimal condition monitoring frequency include: The objective function of the condition monitoring frequency model established with the goal of maximizing the available time of the equipment is max{B}, where B is a function of the monitoring frequency γ, B=f(γ), f(γ) is a functional relationship between the equipment detection frequency and the available time of the equipment, the monitoring frequency is a variable, the available time is a dependent variable, and the optimal monitoring frequency γ satisfies: c min ≤γ≤γ max where γ max , γ min are the maximum and minimum values ​​of the monitoring frequency respectively.

5. The method according to claim 1, wherein the step of determining the sum of expected benefits of the different health states of the device, the state monitoring corresponding to the health states, and the quality control measures corresponding to the health states based on the average duration of the different health states, and determining the optimal quality control measure with the goal of maximizing the sum of expected benefits of the device comprises: With the goal of maximizing the total expected benefits of the equipment, the objective function of the optimal quality control measures model is determined to be: max{G}, where G is the sum of the expected benefits of the different health states, the state monitoring corresponding to the health states, and the quality control measures corresponding to the health states during the entire life cycle of the equipment. 6 . The method according to claim 1 , wherein the time for transitioning between the different health states of the device follows an exponential distribution, and the probability of transitioning between the different health states is constant.

7. A system for equipment status monitoring and quality control measures, the system comprising: An initialization unit, configured to obtain different health states describing the device, and determine, based on the different health states, state monitoring and quality control measures corresponding to the health states; an acquisition unit, configured to acquire, based on historical data, the transition rates of different health states of the device, the expected benefits of different health states of the device, the expected benefits of status monitoring corresponding to the health states, and the expected benefits of the quality control measures corresponding to the health states; a first calculation unit, configured to determine a state frequency of the device staying in the different health states based on a Markov process and calculate an average duration of the device in different health states based on the state frequency; a second calculation unit, configured to determine the available time of the device according to the average duration of the different health states, establish a condition monitoring frequency model with the longest available time of the device as the goal, and determine the optimal condition monitoring frequency; The third calculation unit is used to determine the different health states of the equipment, the expected sum of the state monitoring corresponding to the health states, and the quality control measures corresponding to the health states based on the average duration of the different health states, and determine the optimal quality control measures with the goal of maximizing the expected sum of the expected benefits of the equipment.

8. The system according to claim 7, wherein the expected benefits of the different health states of the equipment are operating benefits obtained by maintaining the health states; The expected benefit of the state monitoring corresponding to the health state is the funds for implementing the state monitoring; The expected benefit of the quality control measures corresponding to the health status is the funds for implementing the maintenance decision.

9. The system according to claim 7, wherein the first computing unit further comprises: The health process of the device is described according to a Markov random process model. The limit state of the health state of the device after n steps is the stable state of the health state of the device. The probability of the stable state after entering the healthy state is a constant, and the probability of the stable state is independent of the initial state of the device. The linear differential equations of the Markov stochastic process are: Among them, λ ij is the transfer rate, P(t) is the Markov general equation, and t is the time; The stationary state probability is obtained by solving the following linear equations: When the device health process reaches the stable state, the average number of times the device stays in the health state i per unit time is the state frequency f of the device in state i. i , the duration T of state i i It refers to the average duration of the equipment staying in state i when the health process reaches a stable state, f ij is the frequency of j transitions to state i, where 10. The system according to claim 7, wherein the second computing unit further comprises: The objective function of the condition monitoring frequency model established with the goal of maximizing the available time of the equipment is max{B}, where B is a function of the monitoring frequency γ, B=f(γ), f(γ) is a functional relationship between the equipment detection frequency and the available time of the equipment, the monitoring frequency is a variable, the available time is a dependent variable, and the optimal monitoring frequency γ satisfies: c min ≤γ≤γ max where γ max , γ min are the maximum and minimum values ​​of the monitoring frequency respectively.

11. The system according to claim 7, wherein the third computing unit further comprises: With the goal of maximizing the total expected benefits of the equipment, the objective function of the optimal quality control measures model is determined to be: max{G}, where G is the sum of the expected benefits of the different health states, the state monitoring corresponding to the health states, and the quality control measures corresponding to the health states during the entire life cycle of the equipment. 12 . The system according to claim 7 , wherein the time for transitioning between the different health states of the device follows an exponential distribution, and the probability of transitioning between the different health states is constant.

Images