New energy equipment system maintenance decision-making method and system based on fault coupling model

Abstract

The invention provides a new energy equipment system maintenance decision-making method and system based on a fault coupling model, and relates to the technical field of equipment predictive maintenance, and the method comprises the steps: collecting system structure information and system fault data of a complex new energy equipment system, and carrying out the maintenance decision-making of the complex new energy equipment system according to the system structure information and the system fault data; respectively constructing a function model view, a system level fault model view and each flow fault model view; constructing a fault coupling model corresponding to the complex new energy equipment system; probability estimation is carried out on the system fault data according to a kernel density estimation method, the fault probability of each fault node in the complex new energy equipment system is obtained, and key fault nodes in all the fault nodes and key node information corresponding to the key fault nodes are obtained; and mapping the key node information into a risk level corresponding to the key node information, and obtaining an optimal maintenance decision based on a decision tree analysis method and a plurality of maintenance decisions. According to the method, multi-dimensional analysis of a complex system can be realized, and fault modes of different components and subsystems can be identified more clearly, so that the fault detection and diagnosis efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of equipment predictive maintenance, and in particular to a maintenance decision method and system for new energy equipment system based on a fault coupling model. Background Art

[0002] Complex systems are formed by the combination and interaction of a large number of simple systems, and there are multi-media coupling relationships such as matter, energy and information between the elements. The activities of complex systems often show characteristics such as emergence, nonlinearity, uncertainty and chaos, and the elements that make up the complex system often show strong coupling. Typical complex systems include power grid systems and complex mechatronics systems. On the one hand, the normal operation of the increasingly developed complex mechatronics systems under predetermined and ideal conditions can bring great convenience to human daily life and social production, but on the other hand, the high structural and functional coupling between component units provides the possibility of fault propagation. During operation, all abnormal states or minor faults in the system can accumulate, amplify, propagate and diffuse in the system, potentially causing a series of chain reactions. If these large-scale complex mechatronics systems fail, they will not be able to achieve the established goals, and may even cause extremely serious safety accidents, endangering the stable and efficient development of the national economy.

[0003] The Chinese patent with announcement number CN112733453B discloses a method, device, readable medium and electronic device for predictive maintenance of equipment based on joint learning, which includes the following steps: determining the model type of the fault prediction model of the target equipment sent by at least two target users; determining the integrated density model and the integrated fault tree model based on the model types corresponding to each of the fault prediction models; determining the proportional coefficients corresponding to the integrated density model and the integrated fault tree model; sending the integrated density model, the integrated fault tree model and the proportional coefficient to each of the target users, so that each of the target users can determine the fault prediction result of the target equipment based on the integrated density model, the integrated fault tree model and the proportional coefficient. However, the method provided by the above application is difficult to effectively monitor some characteristic factors of the complex new energy equipment system, resulting in a small number of effective samples for fault state prediction, and the equipment maintenance influencing factors have the characteristics of fuzziness and uncertainty, resulting in low diagnostic efficiency of equipment fault identification. Therefore, it is very necessary to provide a method and system for tracing the source of wind power equipment faults based on a multi-level model of fault decoupling to improve the accuracy of fault source location. Summary of the invention

[0004] In view of this, the present invention proposes a maintenance decision method and system for new energy equipment system based on fault coupling model. By collecting system structure information and fault data, constructing functional model view, system level fault model view and each flow fault model view, multi-dimensional analysis of complex systems is realized, and the fault modes of different components and subsystems can be more clearly identified, thereby improving the efficiency of fault detection and diagnosis.

[0005] The present invention provides a new energy equipment system maintenance decision method based on a fault coupling model, the method comprising:

[0006] Collecting system structure information and system fault data of complex new energy equipment systems, and constructing a functional model view, a system-level fault model view, and each flow fault model view according to the system structure information and the system fault data;

[0007] Based on the functional model view, the system-level fault model view and the flow fault model view, a fault coupling model corresponding to the complex new energy equipment system is constructed;

[0008] Probability estimation is performed on the system fault data according to a kernel density estimation method to obtain the fault probability of each fault node in the complex new energy equipment system, and key fault nodes among all fault nodes and key node information corresponding to the key fault nodes are obtained;

[0009] The key node information is mapped to a risk level corresponding to the key node information, a plurality of maintenance decisions corresponding to the risk level are obtained, and an optimal maintenance decision is obtained based on a decision tree analysis method and the plurality of maintenance decisions.

[0010] On the basis of the above technical solution, preferably, the function model view, the system level fault model view and each flow fault model view are constructed respectively according to the system structure information and the system fault data, specifically including:

[0011] According to the system structure information, a system structure block diagram of the complex new energy equipment system is obtained, and the system structure block diagram is divided into units based on the IDEF0 functional model analysis method to construct a functional model view;

[0012] Taking different faults in the system fault data as fault nodes, constructing a system-level fault model view;

[0013] Use material flow, energy flow and information flow to connect each fault node respectively and build the fault model view of each flow.

[0014] Based on the above technical solution, preferably, obtaining the key faulty node among all the faulty nodes specifically includes:

[0015] The fault impact of all fault nodes in the fault coupling model on other fault nodes is determined, and the fault impact of each fault node is sorted, and the fault node with the largest fault impact is taken as the key fault node.

[0016] More preferably, the method of performing probability estimation on the system fault data according to the kernel density estimation method to obtain the fault probability of each fault node in the complex new energy equipment system specifically includes:

[0017] Based on the kernel density estimation method in non-parametric estimation, the fault probability density distribution function of each fault node in the complex new energy equipment system is calculated, and the corresponding failure rate of the fault node is calculated according to the fault probability density distribution function.

[0018] More preferably, the expression of the failure rate is:

[0019]

[0020] Where K() represents the Gaussian kernel function used in the kernel density estimator, x represents the value of all possible sample points of the random variable X, and x n represents the nth failure time in the study period, f(x) represents the theoretical probability density, h represents the bandwidth selected in the kernel density estimator, and F(x) represents the failure rate.

[0021] More preferably, the method further comprises:

[0022] Construct the material flow connection relationship matrix, energy flow connection relationship matrix and information flow connection relationship matrix, and calculate the corresponding propagation capacity matrix to obtain the key value and fault propagation coefficient corresponding to each fault node;

[0023] Based on the fault propagation coefficient, a fault diffusion coefficient matrix corresponding to the fault propagation coefficient is obtained, and according to the fault diffusion coefficient matrix and a propagation capacity matrix, a cumulative fault propagation diffusion coefficient is obtained.

[0024] More preferably, the expressions of the fault diffusion coefficient matrix and the cumulative fault propagation diffusion coefficient are:

[0025]

[0026] R H =DD T -I

[0027]

[0028] Where D[i,j] represents all elements from faulty node i to faulty node j in the propagation capacity matrix, and F i (t) represents the failure rate of the i-th fault node within time t, Y[i,j] represents all element values ​​from fault node i to fault node j in the heterogeneous flow connection relationship matrix, n represents the n-th propagation step of the fault propagation process, k represents the k-th propagation step of the fault propagation process, D T represents the transposed matrix of the propagation capacity matrix, and I represents the matrix DD T The diagonal matrix, R H represents the propagation coefficient matrix, represents the fault diffusion coefficient matrix, I2 represents R H *R H The diagonal matrix of CR(v i ,v j ) represents the cumulative fault propagation diffusion coefficient, R H [i,j] represents the fault propagation probability from fault node i to fault node j in the fault propagation coefficient matrix, represents the probability of fault diffusion from fault node i to fault node j in the fault diffusion coefficient matrix, represents the probability of fault diffusion from faulty node i to faulty node j through k steps, and L represents the edge betweenness.

[0029] More preferably, the method further comprises:

[0030] Determine the level of maintenance decision according to the risk level, select maintenance cost index, function impact index and maintenance time index as decision scoring index, and assign attribute weights to the maintenance cost index, the function impact index and the maintenance time index respectively;

[0031] The probability of occurrence of maintenance decisions corresponding to each probability branch of the decision tree is allocated according to the historical fault maintenance records, and each maintenance decision is scored under the maintenance cost index, the functional impact index and the maintenance time index according to the maintenance decision evaluation index scoring rules to draw a decision tree.

[0032] In a second aspect of the present application, a new energy equipment system maintenance decision system based on a fault coupling model is provided, wherein the new energy equipment system maintenance decision system comprises an information collection module, a fault calculation module and a decision optimization module, wherein:

[0033] The information collection module is used to collect system structure information and system fault data of complex new energy equipment systems, and to construct a function model view, a system level fault model view and each flow fault model view according to the system structure information and the system fault data;

[0034] The fault calculation module is used to construct a fault coupling model corresponding to the complex new energy equipment system based on the functional model view, the system level fault model view and the flow fault model view, and to perform probability estimation on the system fault data according to the kernel density estimation method, so as to obtain the fault probability of each fault node in the complex new energy equipment system, and to obtain the key fault nodes among all the fault nodes and the key node information corresponding to the key fault nodes;

[0035] The decision optimization module is used to map the key node information to the risk level corresponding to the key node information, obtain the multiple maintenance decisions corresponding to the risk level, and obtain the optimal maintenance decision based on the decision tree analysis method and the multiple maintenance decisions.

[0036] In a third aspect of the present application, an electronic device is provided, comprising a processor, a memory, a user interface and a network interface, wherein the memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory.

[0037] The maintenance decision method and system for new energy equipment system based on fault coupling model provided by the present invention have the following beneficial effects compared with the prior art:

[0038] (1) By collecting system structure information and fault data, constructing functional model views, system-level fault model views, and flow fault model views, a multi-dimensional analysis of complex systems is achieved, which can more clearly identify the failure modes of different components and subsystems, thereby improving the efficiency of fault detection and diagnosis. By constructing a fault coupling model, the mutual influence and coupling relationship between faults can be intuitively displayed, and key nodes with high failure probability can be identified, thereby significantly reducing the overall failure rate of complex new energy equipment systems. Combined with the decision tree analysis method, the optimal maintenance plan can be determined, which can solve the problems of complex functional structure of complex new energy equipment systems, unclear mutual influence relationships between units, and complex coupling relationships between units and faults, which lead to difficult maintenance decisions, thereby improving the overall adaptability and resilience of complex new energy equipment systems.

[0039] (2) Using the IDEF0 functional model analysis method to divide units can effectively identify and analyze the various functional units of the system. By systematically describing the logical relationship between functions, it helps to find performance bottlenecks, redundant functions or unnecessary complexity, and optimize the system function as a whole. Different faults in the system fault data are used as fault nodes to construct a system-level fault model view, which can clearly show the relationship between different faults and their hierarchy in the system. At the same time, by connecting various fault nodes and constructing each flow fault model view, it can help analyze the propagation path and causal relationship of the fault, thereby improving the accuracy of equipment fault detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0041] Figure 1 A schematic diagram of a flow chart of a maintenance decision method for a new energy equipment system based on a fault coupling model provided by the present invention;

[0042] Figure 2 A schematic diagram of the IDEF0 functional model view provided by the present invention;

[0043] Figure 3 A schematic diagram of a fault coupling model provided by the present invention;

[0044] Figure 4 A schematic diagram of a maintenance solution decision tree provided by the present invention;

[0045] Figure 5 A schematic diagram of the framework of the new energy equipment system maintenance decision system provided by the present invention;

[0046] Figure 6 This is a schematic structural diagram of an electronic device provided by the present invention.

[0047] Explanation of the accompanying reference numerals: 1. New energy equipment system maintenance decision system; 11. Information acquisition module; 12. Fault calculation module; 13. Decision optimization module; 2. Electronic equipment; 21. Processor; 22. Communication bus; 23. User interface; 24. Network interface; 25. Memory. DETAILED DESCRIPTION

[0048] The following will be combined with the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0049] The present invention discloses a maintenance decision method for a new energy equipment system based on a fault coupling model. Figure 1 The method includes steps S1 to S4.

[0050] Step S1, collecting system structure information and system fault data of the complex new energy equipment system, and constructing a functional model view, a system level fault model view and each flow fault model view according to the system structure information and the system fault data.

[0051] In this step, the structural information of the system can be collected through on-site surveys, system design documents, maintenance records, etc., including the structural layout of system components, equipment, and pipelines, as well as the connection relationship between them. At the same time, modeling tools (such as CAD, system simulation software, etc.) can also be used to draw the functional model view of the system and the system-level fault model view to better describe the structure of the system. The fault data of the system can be collected through system historical fault records, fault reports from operation and maintenance personnel, and system logs, including information such as the time when the fault occurred, the type of fault, and the location of the fault. A fault data management system can be established to uniformly archive and classify the collected fault data for subsequent fault analysis. For some key components or nodes with high fault frequencies, more detailed fault data collection methods can be adopted, such as installing sensors to monitor the operating status.

[0052] This step also includes steps S11 to S13.

[0053] Step S11, according to the system structure information, obtain the system structure block diagram of the complex new energy equipment system, and divide the system structure block diagram into units based on the IDEF0 functional model analysis method to construct a functional model view.

[0054] In this step, if Figure 2 As shown, the overall structure of the complex new energy equipment system is analyzed, the various components of the system and their interrelationships are identified, and the structural block diagram of the complex new energy equipment system is drawn according to the analysis results. The IDEF0 functional model analysis method is used to divide the system functions into the smallest functional units, and the functional model view required for the complex new energy equipment fault coupling model is established.

[0055] Step S12: different faults in the system fault data are used as fault nodes to construct a system-level fault model view.

[0056] In this step, according to the system fault data in the complex new energy equipment system, the system fault data includes historical fault records, maintenance records, and expert experience, etc. These data will be used to identify various faults that may occur in the system. The collected system fault data is analyzed to identify various fault modes and use them as nodes. These nodes can be specific faults that occur in the system, such as power failure, control system failure, etc.

[0057] At the same time, each fault is taken as a node, and a system-level fault model is established by dividing it into three layers: system level, component level, and part level. System level: The main functional modules or subsystems in the system are taken as system-level nodes. For example, power supply system, control system, and drive system, etc.; Component level: In each system-level module, specific components are further divided. For example, in the power supply system, components such as transformers, inverters, and batteries can be identified; Part level: At the component level, it is further subdivided into the part level to identify the specific parts of each component. For example, in the inverter, it may include capacitors, inductors, switching elements, etc. The identified fault nodes are organized according to the hierarchical relationship of the system level, component level, and part level to form a three-layer structure.

[0058] The impact of each fault includes local impact, impact on the upper level and impact on the entire system. According to the FMEA concept, the local impact, impact on the upper level and final impact of each fault are analyzed and clarified, and based on this, heterogeneous flows are used to connect the faults.

[0059] Step S13, use material flow, energy flow and information flow to connect each fault node respectively, and build a fault model view of each flow.

[0060] Step S2, constructing a fault coupling model corresponding to the complex new energy equipment system based on the functional model view, the system level fault model view and the flow fault model view.

[0061] In this embodiment, if Figure 3 As shown, the final fault coupling model is a three-layer network structure. From the inside to the outside, there are three layers: subsystem fault, component-level fault and part-level fault. Each fault node is connected by material flow, energy flow and information flow. The material flow is represented by a solid line, the energy flow is represented by a dotted line, and the information flow is represented by a dotted line. Finally, a fault coupling model is established.

[0062] Step S3, perform probability estimation on the system fault data according to the kernel density estimation method, obtain the failure probability of each fault node in the complex new energy equipment system, and obtain the key fault nodes among all the fault nodes and the key node information corresponding to the key fault nodes.

[0063] In this step, the fault impact of all fault nodes in the fault coupling model on other fault nodes is determined, and the fault impact of each fault node is sorted, and the fault node with the largest fault impact is taken as the key fault node.

[0064] The expression of failure rate is:

[0065]

[0066] Where K( ) represents the Gaussian kernel function selected in the kernel density estimator, x represents the value of all possible sample points of the random variable X, and x n represents the nth failure time in the study period, f(x) represents the theoretical probability density, h represents the bandwidth selected in the kernel density estimator, and F(x) represents the failure rate.

[0067] This step also includes steps S31 to S32.

[0068] Step S31, constructing a material flow connection relationship matrix, an energy flow connection relationship matrix and an information flow connection relationship matrix, and calculating the corresponding propagation capacity matrix to obtain the key value and fault propagation coefficient corresponding to each fault node.

[0069] In this step, the connection relationship matrix of the faults of system components is calculated. The connection edges between faults include three heterogeneous flow connection relationships: material flow, energy flow, and information flow. Different heterogeneous flow connection relationships have different fault propagation modes. The fault propagation connection relationship matrix that needs to be established includes the material flow connection relationship matrix, the energy flow connection relationship matrix, the information flow connection relationship matrix, and the connection relationship matrix in which all heterogeneous flows exist. Taking the material flow connection relationship matrix as an example, it is represented by M, where the element value M[i,j] represents the element value of the i-th row and j-th column of the matrix M, and is defined as follows:

[0070]

[0071] Similarly, the definitions of the element value E[i,j] of the energy flow connection relationship matrix E, the element value I[i,j] of the information flow connection relationship matrix I, and the element value Y[i,j] of the connection relationship matrix Y containing all heterogeneous flows are as follows:

[0072]

[0073]

[0074] The fault propagation capabilities of the same component at different levels in the hierarchical model will be different. Based on the hierarchical structure model of fault propagation, the more related faults appear in the system components, the greater the possibility of fault propagation, and the corresponding stronger fault propagation capability.

[0075] In this step, the fault impact of all fault nodes in the fault coupling model on other fault nodes is determined, and the fault impact of each fault node is sorted, and the fault node with the largest fault impact is taken as the key fault node.

[0076] Furthermore, for any time t, by comparing the sum of the fault impacts of all system component nodes on other system component nodes in the fault coupling model, the larger the value, the more critical it is. Based on this, the critical fault node can be determined;

[0077] For the key nodes in the fault propagation process, the fault coupling model of the complex new energy equipment system is used to determine the various system component nodes connected to the fault root node. According to the definition of fault impact, a known fault will choose an edge with a larger fault impact value for propagation and diffusion. Therefore, by comparing the fault impact values ​​of the edges formed by the various system component nodes connected to the fault root node at this time, the larger the value, the more critical it is;

[0078] For the final node of fault propagation, the fault coupling model is combined to determine the topmost node to which the system component fault can propagate. At the same time, consider whether the fault propagation probability of each node in the system after the system fault propagates k steps is less than 10. -8 ,Comparing the cumulative fault propagation diffusion coefficient of each fault path, the fault path with a larger value is more critical, and the final critical node of the fault path propagation can be determined based on this finding.

[0079] Step S32: based on the fault propagation coefficient, a fault diffusion coefficient matrix corresponding to the fault propagation coefficient is obtained, and according to the fault diffusion coefficient matrix and the propagation capacity matrix, a cumulative fault propagation diffusion coefficient is obtained.

[0080] In this embodiment, the expressions of the fault diffusion coefficient matrix and the cumulative fault propagation diffusion coefficient are:

[0081]

[0082] R H =DD T -I

[0083]

[0084] Where D[i,j] represents all elements from faulty node i to faulty node j in the propagation capacity matrix, and F i(t) represents the failure rate of the i-th fault node within time t, Y[i,j] represents all element values ​​from fault node i to fault node j in the heterogeneous flow connection relationship matrix, n represents the n-th propagation step of the fault propagation process, k represents the k-th propagation step of the fault propagation process, D T represents the transposed matrix of the propagation capacity matrix, and I represents the matrix DD T The diagonal matrix, R H represents the propagation coefficient matrix, represents the fault diffusion coefficient matrix, I2 represents R H *R H The diagonal matrix of CR(v i ,v j ) represents the cumulative fault propagation diffusion coefficient, R H [i,j] represents the fault propagation probability from fault node i to fault node j in the fault propagation coefficient matrix, represents the probability of fault diffusion from fault node i to fault node j in the fault diffusion coefficient matrix, represents the probability of fault diffusion from faulty node i to faulty node j through k steps, and L represents the edge betweenness.

[0085] In an example, the propagation capacity matrix D uses the correlation properties of the correlation matrix to calculate the fault propagation capacity of system components at all levels. The elements in the matrix D are represented as D[i,j], and the calculation formula is:

[0086]

[0087] Among them, D[i,j]∈[0,1].

[0088] The stronger the fault propagation capability of a system component, the greater the chance that the fault will propagate to other system components, and the larger the corresponding element value D[i,j] in the matrix. In order to obtain the key fault node in the system, since the element value D[i,j] in the fault propagation matrix D represents the ability of the fault to propagate to another fault, the sum of each row in the fault propagation capability matrix is ​​defined as the key value of the fault node. The calculation formula is:

[0089]

[0090] Since the fault propagation occurs between system components, the fault propagation coefficient is used to describe the ability of system components to propagate faults to specific components. The magnitude of the fault propagation coefficient is related to the fault propagation capabilities of the two system components involved in the fault propagation. The propagation coefficient matrix R H The calculation formula is:

[0091] R H =DD T -I

[0092] Among them, D T is the transposed matrix of matrix D, I is the matrix DD T The diagonal matrix of .

[0093] Given that fault propagation occurs between different system components, the diagonal element values ​​in the fault propagation coefficient matrix should no longer be considered and are set to 0, R H [i,j] in the matrix R H It can be expressed as:

[0094]

[0095] The propagation coefficient matrix represents the situation of direct fault propagation between different system components, in which no further propagation of the fault occurs. In the real process, the fault will not only propagate once, but also spread further. The system components that are not directly connected can transmit the fault through the intermediate common system components, thus forming multi-step faults in the fault propagation hierarchy.

[0096] The fault diffusion coefficient matrix is ​​calculated by combining the distributed diffusion principle and applying the step length of the fault diffusion path. The calculation formula is:

[0097]

[0098] Where I2 is R H *R H The diagonal matrix of For v i to v j The probability of two-step fault propagation. If the element satisfies Then the system component v i to v j There is no two-step fault propagation. At the same time, the k-step fault diffusion coefficient matrix is Fault from v i to v j The probability of a fault spreading through k steps is given by the element to express;

[0099] Assume that node v i Spread the failure to node v j , when the fault spreads from the (k-1)th step to the kth step, the failure probability of the system component at the kth step is based on the conditional failure probability of the system component at the (k-1)th step, and the calculation formula is:

[0100]

[0101] The sum of the direct fault propagation coefficient and the indirect fault propagation coefficient (i.e., diffusion coefficient) of the system components is defined as the cumulative fault propagation diffusion coefficient CR (vi ,v j ), used to express system components v i After a fault occurs, it propagates and diffuses to system components v through k steps. j The cumulative value is calculated as follows:

[0102]

[0103] From a probability perspective, the fault may be transmitted to the top node of the complex equipment system along the hierarchical model. However, due to the functional characteristics of the complex equipment system, when the fault propagation probability is less than 10 -8 The fault will no longer propagate.

[0104] The edge betweenness is used to measure the importance of the edge position in the entire structural model. The larger the edge betweenness, the greater the load on the edge, and the more likely it is to cause rapid fault propagation. The calculation formula is:

[0105]

[0106] Among them, δ ok For component v o and v k The number of shortest paths between .

[0107] The larger the fault impact value is, the easier it is for the fault to pass through the edge and have a serious impact on the entire system. Based on the fault coupling model of fault propagation, the calculation equation of the fault impact degree is Q(v i ,v j ) The calculation formula for the complex system is:

[0108]

[0109] Step S4, mapping the key node information to the risk level corresponding to the key node information, obtaining multiple maintenance decisions corresponding to the risk level, and obtaining the optimal maintenance decision based on the decision tree analysis method and the multiple maintenance decisions.

[0110] In this embodiment, the required repair and maintenance method is determined according to the importance of the probability of the fault mode, and the ranking result of the key fault nodes of the multi-stream coexistence connection is used as a basis. The fault modes ranked in the first 1 / 3 are classified as the I fault mode maintenance level, the fault modes ranked in the middle 1 / 3 are classified as the II fault mode maintenance level, and the fault modes ranked in the last 1 / 3 are classified as the III fault mode maintenance level. According to the repair and maintenance method of each fault mode, its nature is classified into repair and restoration type, failure abnormality type, design and installation type, and operating condition type.

[0111] For level I failures: Because the probability level of this level of failure is high, it is easier to occur and more active maintenance measures need to be taken.

[0112] For level II faults: the occurrence of this level of faults may be affected by the continuous changes in operating conditions, operating conditions, and operating environment, and has a certain degree of randomness.

[0113] For level III faults: the probability of occurrence of this level of faults is less than 1%, and they are generally not major faults that have a significant impact on the system. Therefore, most of these faults are repaired after the fact. For faults caused by deterioration of operating conditions, repairs are selected based on the situation.

[0114] This step also includes steps S41 to S42.

[0115] Step S41, determining the level of maintenance decision according to the risk level, selecting maintenance cost index, function impact index and maintenance time index as decision scoring indexes, and assigning attribute weights to the maintenance cost index, function impact index and maintenance time index accordingly.

[0116] Step S42, the probability of occurrence of maintenance decisions corresponding to each decision tree probability branch is allocated according to the historical fault maintenance records, and each maintenance decision is scored under the maintenance cost index, function impact index and maintenance time index according to the maintenance decision evaluation index scoring rules to draw a decision tree.

[0117] In this step, the decision node of the decision tree is a square, and several straight lines can be drawn from the decision node. Each straight line is called a decision branch, and each decision branch represents a strategy. The state node of the decision tree is a circle, and several straight lines can be drawn from the state node. Each straight line is called a probability branch, which represents a state with a probability of occurrence. If there is no state node after the plan branch, it means that each plan has a certain result. The component that needs to be considered when evaluating the maintenance plan is the plan attribute, which is listed on the right side of the decision tree in a list.

[0118] Select maintenance cost (MC), functional impact (PI) and maintenance time (MT), divide the maintenance level according to the risk level of the failure mode, assign attribute weights to the above three indicators, and assign the probability of occurrence of each plan corresponding to each decision tree probability branch according to the historical failure maintenance record. Refer to the scoring rules of maintenance plan evaluation indicators to score the nth maintenance plan under the above three indicators, and draw the following Figure 4 The decision tree shown.

[0119] Maintenance income S n It represents the quantitative effect of maintenance results and impacts, and the calculation formula is:

[0120] Sn =a n1 W PI +a n2 W MT + an 3W MC

[0121] Among them, a n1 、a n2 、a n3 The scores of the nth maintenance plan under the above three indicators are respectively: PI , W MT , W MC is the attribute weight of the above three indicators. The maintenance benefit S calculated by the above formula n To determine the specific maintenance plan for a certain failure mode, the maintenance benefit S n The higher the value of S, the more reasonable the maintenance plan is. n The lower the value, the more unreasonable it is.

[0122] By collecting system structure information and fault data, constructing functional model views, system-level fault model views and flow fault model views, we can achieve multi-dimensional analysis of complex systems, more clearly identify the failure modes of different components and subsystems, and thus improve the efficiency of fault detection and diagnosis. By constructing a fault coupling model, we can intuitively display the mutual influence and coupling relationship between faults, identify key nodes with high failure probability, and thus significantly reduce the overall failure rate of complex new energy equipment systems. Combined with the decision tree analysis method to determine the best repair and maintenance plan, we can solve the problems of complex functional structure of complex new energy equipment systems, unclear mutual influence relationships between units, and complex coupling relationships between units and faults, which lead to difficult maintenance decisions, thereby improving the overall adaptability and resilience of complex new energy equipment systems.

[0123] Based on the above method, the embodiment of the present application discloses a new energy equipment system maintenance decision system based on a fault coupling model, referring to Figure 5 The new energy equipment system maintenance decision system 1 includes an information collection module 11, a fault calculation module 12 and a decision optimization module 13, wherein:

[0124] The information collection module 11 is used to collect system structure information and system fault data of complex new energy equipment systems, and to construct a functional model view, a system level fault model view, and each flow fault model view according to the system structure information and system fault data;

[0125] The fault calculation module 12 is used to construct a fault coupling model corresponding to the complex new energy equipment system based on the function model view, the system level fault model view and the flow fault model view, and to perform probability estimation on the system fault data according to the kernel density estimation method, so as to obtain the fault probability of each fault node in the complex new energy equipment system, and obtain the key fault nodes among all the fault nodes and the key node information corresponding to the key fault nodes;

[0126] The decision optimization module 13 is used to map the key node information to the risk level corresponding to the key node information, obtain multiple maintenance decisions corresponding to the risk level, and obtain the optimal maintenance decision based on the decision tree analysis method and multiple maintenance decisions.

[0127] In one example, the information acquisition module 11 is used to obtain the system structure block diagram of a complex new energy equipment system based on the system structure information, and divide the system structure block diagram into units based on the IDEF0 functional model analysis method to construct a functional model view; different faults in the system fault data are used as fault nodes to construct a system-level fault model view; material flow, energy flow and information flow are used to connect each fault node respectively to construct each flow fault model view.

[0128] In one example, the fault calculation module 12 is used to determine the fault impact of all fault nodes in the fault coupling model on other fault nodes, and sort the fault impact of each fault node, and select the fault node with the largest fault impact as the key fault node.

[0129] In one example, the fault calculation module 12 is used to calculate the fault probability density distribution function of each fault node in the complex new energy equipment system based on the kernel density estimation method in non-parametric estimation, and calculate the corresponding failure rate of the fault node according to the fault probability density distribution function.

[0130] In one example, the expression for the failure rate is:

[0131]

[0132] Where K() represents the Gaussian kernel function used in the kernel density estimator, x represents the value of all possible sample points of the random variable X, and x n represents the nth failure time in the study period, f(x) represents the theoretical probability density, h represents the bandwidth selected in the kernel density estimator, and F(x) represents the failure rate.

[0133] In one example, the fault operation module 12 is used to construct a material flow connection relationship matrix, an energy flow connection relationship matrix, and an information flow connection relationship matrix, and calculate the corresponding propagation capacity matrix to obtain the key value and fault propagation coefficient corresponding to each fault node; based on the fault propagation coefficient, obtain the fault diffusion coefficient matrix corresponding to the fault propagation coefficient, and according to the fault diffusion coefficient matrix and the propagation capacity matrix, obtain the cumulative fault propagation diffusion coefficient.

[0134] In one example, the expressions for the fault diffusion coefficient matrix and the cumulative fault propagation diffusion coefficient are:

[0135]

[0136] R H =DD T -I

[0137]

[0138] Where D[i,j] represents all elements from faulty node i to faulty node j in the propagation capacity matrix, and F i (t) represents the failure rate of the i-th fault node within time t, Y[i,j] represents all element values ​​from fault node i to fault node j in the heterogeneous flow connection relationship matrix, n represents the n-th propagation step of the fault propagation process, k represents the k-th propagation step of the fault propagation process, D T represents the transposed matrix of the propagation capacity matrix, and I represents the matrix DD T The diagonal matrix, R H represents the propagation coefficient matrix, represents the fault diffusion coefficient matrix, I2 represents R H *R H The diagonal matrix of CR(v i ,v j ) represents the cumulative fault propagation diffusion coefficient, R H [i,j] represents the fault propagation probability from fault node i to fault node j in the fault propagation coefficient matrix, represents the probability of fault diffusion from fault node i to fault node j in the fault diffusion coefficient matrix, represents the probability of fault diffusion from faulty node i to faulty node j through k steps, and L represents the edge betweenness.

[0139] In one example, the decision optimization module 13 is used to determine the level of maintenance decisions according to the risk level, select the maintenance cost indicator, function impact indicator and maintenance time indicator as decision scoring indicators, and assign attribute weights to the maintenance cost indicator, function impact indicator and maintenance time indicator respectively; the probability of occurrence of maintenance decisions corresponding to each decision tree probability branch is allocated according to the historical fault maintenance record, and each maintenance decision is scored under the maintenance cost indicator, function impact indicator and maintenance time indicator according to the maintenance decision evaluation indicator scoring rules to draw a decision tree.

[0140] See also Figure 6 , is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Figure 6 As shown, the electronic device 2 may include: at least one processor 21 , at least one network interface 24 , a user interface 23 , a memory 25 , and at least one communication bus 22 .

[0141] The communication bus 22 is used to realize the connection and communication between these components.

[0142] The user interface 23 may include a display screen (Display) and a camera (Camera), and the optional user interface 23 may also include a standard wired interface and a wireless interface.

[0143] The network interface 24 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0144] Among them, the processor 21 may include one or more processing cores. The processor 21 uses various interfaces and lines to connect various parts in the entire server, and executes various functions of the server and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 25, and calling data stored in the memory 25. Optionally, the processor 21 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor 21 can integrate one or more combinations of a central processing unit (Central Processing Unit, CPU), a graphics processor (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 21, and it can be implemented separately through a chip.

[0145] Among them, the memory 25 may include a random access memory (Random Access Memory, RAM) and may also include a read-only memory (Read-Only Memory). Optionally, the memory 25 includes a non-transitory computer-readable storage medium. The memory 25 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 25 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned method embodiments, etc.; the data storage area may store data involved in the above-mentioned method embodiments, etc. The memory 25 may also be optionally at least one storage device located away from the aforementioned processor 21. As Figure 6 As shown, the memory 25 as a computer storage medium may include an operating system, a network communication module, a user interface module, and an application program of a new energy equipment system maintenance decision method based on a fault coupling model.

[0146] exist Figure 6In the electronic device 2 shown, the user interface 23 is mainly used to provide an input interface for the user and obtain data input by the user; and the processor 21 can be used to call an application program stored in the memory 25 for a new energy equipment system maintenance decision method based on a fault coupling model. When executed by one or more processors, the electronic device executes one or more methods in the above-mentioned embodiments.

[0147] A computer-readable storage medium stores instructions, which, when executed by one or more processors, enable the computer to execute one or more methods in the above-mentioned embodiments.

[0148] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the order of the actions described, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required for the present application.

[0149] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0150] In the several embodiments provided in this application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0151] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0152] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0153] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a memory and includes several instructions for a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the various embodiments of the present application. The aforementioned memory includes: various media that can store program codes, such as USB flash drives, mobile hard drives, magnetic disks or optical disks.

[0154] The above are only exemplary embodiments of the present disclosure, and the scope of the present disclosure cannot be limited thereto. That is, any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. After considering the disclosure of the specification and the truth of practice, it will be easy for those skilled in the art to think of other embodiments of the present disclosure. This application is intended to cover any variation, use or adaptive change of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary techniques in the technical field that are not recorded in the present disclosure.

[0155] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A maintenance decision method for new energy equipment system based on fault coupling model, characterized in that: The method comprises: Collecting system structure information and system fault data of complex new energy equipment systems, and constructing a functional model view, a system level fault model view, and each flow fault model view according to the system structure information and the system fault data; Based on the functional model view, the system-level fault model view and the flow fault model view, a fault coupling model corresponding to the complex new energy equipment system is constructed; Probability estimation is performed on the system fault data according to a kernel density estimation method to obtain the fault probability of each fault node in the complex new energy equipment system, and key fault nodes among all fault nodes and key node information corresponding to the key fault nodes are obtained; The key node information is mapped to a risk level corresponding to the key node information, a plurality of maintenance decisions corresponding to the risk level are obtained, and an optimal maintenance decision is obtained based on a decision tree analysis method and the plurality of maintenance decisions.

2. The method according to claim 1, characterized in that The constructing of a function model view, a system level fault model view and each flow fault model view according to the system structure information and the system fault data specifically includes: According to the system structure information, a system structure block diagram of the complex new energy equipment system is obtained, and the system structure block diagram is divided into units based on the IDEF0 functional model analysis method to construct a functional model view; Taking different faults in the system fault data as fault nodes, constructing a system-level fault model view; Use material flow, energy flow and information flow to connect each fault node respectively and build the fault model view of each flow.

3. The method according to claim 1, characterized in that The obtaining of the key faulty nodes among all the faulty nodes specifically includes: The fault impact of all fault nodes in the fault coupling model on other fault nodes is determined, and the fault impact of each fault node is sorted, and the fault node with the largest fault impact is taken as the key fault node.

4. The method according to claim 1, characterized in that The method of performing probability estimation on the system fault data according to the kernel density estimation method to obtain the fault probability of each fault node in the complex new energy equipment system specifically includes: Based on the kernel density estimation method in non-parametric estimation, the fault probability density distribution function of each fault node in the complex new energy equipment system is calculated, and the corresponding failure rate of the fault node is calculated according to the fault probability density distribution function.

5. The method according to claim 4, characterized in that The expression of the failure rate is: Where K() represents the Gaussian kernel function used in the kernel density estimator, x represents the value of all possible sample points of the random variable X, and x n represents the nth failure time in the study period, f(x) represents the theoretical probability density, h represents the bandwidth selected in the kernel density estimator, and F(x) represents the failure rate.

6. The method according to claim 4, characterized in that The method further comprises: Construct the material flow connection relationship matrix, energy flow connection relationship matrix and information flow connection relationship matrix, and calculate the corresponding propagation capacity matrix to obtain the key value and fault propagation coefficient corresponding to each fault node; Based on the fault propagation coefficient, a fault diffusion coefficient matrix corresponding to the fault propagation coefficient is obtained, and according to the fault diffusion coefficient matrix and a propagation capacity matrix, a cumulative fault propagation diffusion coefficient is obtained.

7. The method according to claim 6, characterized in that The expressions of the fault diffusion coefficient matrix and the cumulative fault propagation diffusion coefficient are: R H =DD T -I Where D[i,j] represents all elements from faulty node i to faulty node j in the propagation capacity matrix, and F i (t) represents the failure rate of the i-th fault node within time t, Y[i,j] represents all element values ​​from fault node i to fault node j in the heterogeneous flow connection relationship matrix, n represents the n-th propagation step of the fault propagation process, k represents the k-th propagation step of the fault propagation process, D T represents the transposed matrix of the propagation capacity matrix, and I represents the matrix DD T The diagonal matrix, R H represents the propagation coefficient matrix, represents the fault diffusion coefficient matrix, I2 represents R H *R H The diagonal matrix of CR(v i ,v j ) represents the cumulative fault propagation diffusion coefficient, R H [i,j] represents the fault propagation probability from fault node i to fault node j in the fault propagation coefficient matrix, represents the probability of fault diffusion from fault node i to fault node j in the fault diffusion coefficient matrix, represents the probability of fault diffusion from faulty node i to faulty node j through k steps, and L represents the edge betweenness.

8. The method according to claim 1, characterized in that The method further comprises: Determine the level of maintenance decision according to the risk level, select maintenance cost index, function impact index and maintenance time index as decision scoring index, and assign attribute weights to the maintenance cost index, the function impact index and the maintenance time index respectively; The probability of occurrence of maintenance decisions corresponding to each probability branch of the decision tree is allocated according to the historical fault maintenance records, and each maintenance decision is scored under the maintenance cost index, the functional impact index and the maintenance time index according to the maintenance decision evaluation index scoring rules to draw a decision tree.

9. A maintenance decision system for new energy equipment system based on fault coupling model, characterized in that: The new energy equipment system maintenance decision system (1) comprises an information collection module (11), a fault calculation module (12) and a decision optimization module (13), wherein: The information collection module (11) is used to collect system structure information and system fault data of the complex new energy equipment system, and to construct a function model view, a system level fault model view and each flow fault model view according to the system structure information and the system fault data; The fault calculation module (12) is used to construct a fault coupling model corresponding to the complex new energy equipment system based on the functional model view, the system level fault model view and the flow fault model view, perform probability estimation on the system fault data according to a kernel density estimation method, obtain the fault probability of each fault node in the complex new energy equipment system, and obtain key fault nodes among all fault nodes and key node information corresponding to the key fault nodes; The decision optimization module (13) is used to map the key node information to a risk level corresponding to the key node information, obtain the multiple maintenance decisions corresponding to the risk level, and obtain the optimal maintenance decision based on a decision tree analysis method and the multiple maintenance decisions.

10. An electronic device, characterized in that: The electronic device (2) comprises a processor (21), a memory (25), a user interface (23) and a network interface (24), wherein the memory (25) is used to store instructions, the user interface (23) and the network interface (24) are used to communicate with other devices, and the processor (21) is used to execute the instructions stored in the memory (25) so that the electronic device (2) executes the method according to any one of claims 1 to 8.

Images