Elevator fault classification method and system

Abstract

The invention discloses an elevator fault classification method and system, and relates to the field of fault data classification. The invention classifies elevator faults from the single aspects of electrical faults, mechanical faults and operational faults; collects multiple groups of historical state parameter data of mechanical components and electrical components of the test elevator, clusters the state parameter data, assigns a grade to each type obtained by clustering, and provides a basis for subsequently determining the fault level corresponding to the state parameter data of the mechanical components and electrical components of the elevator to be classified, and then determines the fault category of the elevator to be classified; predicts the future state parameter data and operational parameter data of the mechanical components and electrical components of the elevator to be classified, and then obtains whether the elevator to be classified will fail at a future moment, and then timely measures can be taken for maintenance.

Description

Technical Field

[0001] The present invention belongs to the field of fault data classification, and in particular, relates to an elevator fault classification method and system. Background Art

[0002] Classifying elevator fault data is a relatively important part of elevator maintenance. Without classification, maintenance personnel will find it difficult to diagnose problems quickly and accurately, increasing maintenance time and costs. It will also be difficult to identify and resolve potential safety hazards, increasing the possibility of accidents. It will also be difficult to develop effective preventive maintenance plans, shortening the service life of the elevator. Summary of the invention

[0003] In view of the problems in the related art, the present invention proposes an elevator fault classification method and system to overcome the above technical problems existing in the existing related art.

[0004] In order to solve the above technical problems, the present invention is achieved through the following technical solutions:

[0005] The present invention is a method and system for classifying elevator faults, comprising the following steps:

[0006] S1. Set several types of mechanical components, electrical components and state parameter types corresponding to the operation stages to obtain an elevator mechanical component state parameter type matrix, an elevator electrical component state parameter type matrix and an elevator operation state parameter type set;

[0007] S2. According to the elevator mechanical component state parameter type matrix and the elevator electrical component state parameter type matrix, the state parameter data of each mechanical component and electrical component in the operation process of several groups of test elevators are collected, and then the error degree data between them and the corresponding standard state parameter data matrix are respectively calculated and clustered to obtain the mechanical component state parameter error cluster center data matrix set and the electrical component state parameter error cluster center data matrix set;

[0008] S3, setting the mechanical component state level and the electrical component state level for the mechanical component state parameter error cluster center data matrix set and the electrical component state parameter error cluster center data matrix set to obtain a mechanical component state level set and an electrical component state level set;

[0009] S4. Collecting real-time and historical status parameter data of the elevator to be classified according to the elevator mechanical component status parameter type matrix, the elevator electrical component status parameter type matrix and the elevator operation status parameter type set;

[0010] S5. Predict the state data at a future time according to the historical state parameter data of the elevator to be classified, and calculate the error degree between the prediction result and the real-time state data of the elevator to be classified and the standard state parameter, and then classify them according to the data matrix set of the cluster center of the mechanical component state parameter error and the data matrix set of the cluster center of the electrical component state parameter error, to obtain the real-time mechanical component state level data, the real-time electrical component state level data, the future mechanical component state level data set and the future electrical component state level data set;

[0011] S6. Determine the fault type of the elevator to be classified according to the real-time mechanical component status level data, the real-time electrical component status level data, the future mechanical component status level data set, and the future electrical component status level data set.

[0012] Preferably, the S1 comprises the following steps:

[0013] S11. Set several types of mechanical components, electrical components and operation stages of the elevator to obtain a set of elevator mechanical component types. , Elevator electrical component type set And the elevator operation stage set , a 1i represents the i-th type of mechanical components of the given elevator, Indicates the total number of mechanical component types of the set elevator; a 3i represents the i-th type of electrical components of the set elevator, Indicates the total number of electrical component types of the set elevator; a 21 、a 22 、a 23 、a 24 、a 25 They represent the parking phase, the acceleration phase, the uniform speed phase and the deceleration phase respectively;

[0014] S12, setting a number of state parameter types related to elevator operation for each elevator mechanical component type in the elevator mechanical component type set, and obtaining an elevator mechanical component state parameter type matrix ; Then set several state parameter types related to elevator operation for each elevator electrical component type in the elevator electrical component type set to obtain an elevator electrical component state parameter type matrix ; , They are as follows:

[0015] ; ;

[0016] in, represents the state parameter type of the jth type of the i-th elevator mechanical component type in the elevator mechanical component type set, b i represents the total number of state parameter types of the i-th elevator mechanical component type in the elevator mechanical component type set; represents the state parameter type of the jth type of the i-th elevator electrical component type in the elevator electrical component type set, represents the total number of state parameter types of the i-th elevator electrical component type in the elevator electrical component type set;

[0017] Then set several state parameter types corresponding to each elevator operation stage in the elevator operation stage set to obtain an elevator operation state parameter type set , Indicates the i-th state parameter type corresponding to each elevator operation stage in the set elevator operation stage set, Indicates the total number of status parameter types corresponding to each elevator operation stage in the set elevator operation stage set.

[0018] Preferably, S2 comprises the following steps:

[0019] S21, setting a test elevator; collecting several groups of historical state parameter data of each mechanical component and electrical component of the test elevator during operation according to the elevator mechanical component state parameter type matrix and the elevator electrical component state parameter type matrix, and obtaining a historical mechanical component state parameter data matrix set And the historical electrical component status parameter data matrix set , , They respectively represent the mechanical component state parameter data matrix and the electrical component state parameter data matrix during the k-th historical operation of the test elevator, Indicates the total number of historical running processes of the test elevator collected; sets the standard state parameter data of each mechanical component and electrical component of the test elevator to obtain the historical mechanical component standard state parameter data matrix and historical electrical component standard state parameter data matrix ; , , , They are as follows:

[0020] ; ;

[0021] ; ;

[0022] in, , Respectively , State parameter data of the jth type of the i-th elevator mechanical component type; , Respectively , Standard state parameter data of the jth type of the i-th elevator mechanical component type;

[0023] S22, respectively calculating the error degree data between each historical mechanical component state parameter data matrix in the historical mechanical component state parameter data matrix set and the historical mechanical component standard state parameter data matrix, and the error degree data between each historical electrical component state parameter data matrix in the historical electrical component state parameter data matrix set and the historical electrical component standard state parameter data matrix, to obtain the historical mechanical component state parameter error degree data matrix set. And the historical electrical component state parameter error degree data matrix set , , The data matrices respectively represent the error degree data matrices between the mechanical component state parameter data matrix and the electrical component state parameter data matrix during the k-th historical operation of the test elevator and the corresponding standard state parameter data matrix; they are as follows:

[0024] ; ;

[0025] in, , Respectively , The error degree between the state parameter data of the jth type of the i-th elevator mechanical component type and the corresponding standard state parameter data; the calculation formulas are as follows:

[0026] ; ;

[0027] S23, clustering the historical mechanical component state parameter error degree data matrix set and the historical electrical component state parameter error degree data matrix set to obtain a mechanical component state parameter error cluster center data matrix set And the electrical component state parameter error cluster center data matrix set , c 1k 、c 2kThey respectively represent the kth mechanical component state parameter error cluster center data matrix and the electrical component state parameter error cluster center data matrix obtained by clustering the historical mechanical component state parameter error degree data matrix set and the historical electrical component state parameter error degree data matrix set, , represents the total number of mechanical component state parameter error cluster center data matrices and electrical component state parameter error cluster center data matrices obtained by clustering the historical mechanical component state parameter error degree data matrix set and the historical electrical component state parameter error degree data matrix set; c 1k 、c 2k They are as follows:

[0028] ; ;

[0029] Among them, c 1kij 、c 2kij Respectively represent c 1k 、c 2k The state parameter error data of the i-th elevator mechanical component type and the j-th type of electrical component type.

[0030] Preferably, the S23 comprises the following steps:

[0031] S231, build component status data cluster center to calculate honey badger population , Indicates that the cluster center of the component status data calculates the i-th honey badger in the honey badger population, Indicates the size of the honey badger population calculated by the cluster center of the component status data; sets the maximum number of iterations for calculating the honey badger population by the cluster center of the component status data to d1 and the current number of iterations to d2, which are recorded as the maximum number of iterations for clustering calculation and the current number of iterations for clustering calculation respectively; the search space dimension for calculating the honey badger population by the cluster center of the component status data is ;

[0032] S232, randomly select a number of historical mechanical component state parameter error degree data matrices and historical electrical component state parameter error degree data matrices from the historical mechanical component state parameter error degree data matrix set and the historical electrical component state parameter error degree data matrix set as component state data clustering centers to calculate the initial position of each honey badger in the honey badger population, and obtain a first initial position matrix set , Indicates the cluster center of the component status data calculation in the honey badger population The initial position matrix of a honey badger is as follows:

[0033] ; ;

[0034] ;

[0035] in, , Respectively Middle A data matrix of cluster centers of errors in state parameters of mechanical components and a data matrix of cluster centers of errors in state parameters of electrical components; , Respectively , State parameter error data of the i-th elevator mechanical component type and the j-th type of electrical component type;

[0036] S233, constructing a component state data clustering center according to the historical mechanical component state parameter error degree data matrix set and the historical electrical component state parameter error degree data matrix set to calculate the first Fitness function of a honey badger ;as follows:

[0037] ;

[0038] In the formula, , They respectively represent the overall discreteness of the historical mechanical component state parameter error degree data matrix set and the historical electrical component state parameter error degree data matrix set; the calculation formulas are as follows:

[0039] ;

[0040] ;

[0041] S234, start iteration, before iteration, set the current iteration number of the cluster calculation to 1; in the first round of iteration, use the cluster center of the component status data to calculate the first Fitness function of a honey badger Calculate the fitness value of the initial position matrix of each honey badger in the first initial position matrix set to obtain a first fitness value set; use the maximum fitness value in the first fitness value set and the corresponding initial position matrix of the honey badger as the first global optimal fitness and the first global optimal position respectively; update the initial position matrix of each honey badger in the first initial position matrix set according to the first global optimal fitness and the first global optimal position; after the update is completed, add 1 to the current iteration number of the cluster calculation and enter the next round of iteration;

[0042] In each other round of iteration, the cluster center of the component status data is used to calculate the first Fitness function of a honey badger Calculate the fitness value of the position matrix of each honey badger in the honey badger population calculated by the cluster center of the component status data updated in the previous iteration process to obtain a second fitness value set; use the maximum fitness value in the second fitness value set and the corresponding position matrix of the honey badger as the second global optimal fitness and the second global optimal position respectively; update the position matrix of each honey badger in the honey badger population calculated by the cluster center of the component status data updated in the previous iteration process according to the second global optimal fitness and the second global optimal position; after the update is completed, add 1 to the current iteration number of the cluster calculation and enter the next iteration;

[0043] S235, when When , the iteration stops, and the data matrix set of the cluster center of the state parameter error of the mechanical component and the data matrix set of the cluster center of the state parameter error of the electrical component are obtained; otherwise, the iteration continues until until the time;

[0044] The honey badger optimization algorithm can conduct extensive searches in the search space by simulating the foraging behavior of honey badgers, thereby effectively avoiding falling into the local optimal solution; and can dynamically adjust the search step size during the search process, thereby accelerating the convergence speed of the algorithm; it has less dependence on initial conditions, and even under poor initial solutions, it can find the global optimal solution through its unique search strategy; based on the above advantages, the honey badger optimization algorithm is used in this scheme to iteratively adjust multiple clustering center data of the historical mechanical component state parameter error degree data matrix set and the historical electrical component state parameter error degree data matrix set for multiple times, and the overall discrete degree of the historical mechanical component state parameter error degree data matrix set and the historical electrical component state parameter error degree data matrix set is used as the fitness function; therefore, as the iteration proceeds, the discrete degree of the historical mechanical component state parameter error degree data matrix set and the historical electrical component state parameter error degree data matrix set becomes smaller and smaller, which indicates that the clustering effect is getting better and better.

[0045] Preferably, S3 comprises the following steps:

[0046] S31, setting a corresponding mechanical component state level and electrical component state level for each state parameter error cluster center data matrix in the mechanical component state parameter error cluster center data matrix set and the electrical component state parameter error cluster center data matrix set, to obtain a mechanical component state level set and electrical component status level sets , , Indicates the set i-th mechanical component status level and electrical component status level.

[0047] Preferably, S4 comprises the following steps:

[0048] S41, elevators to be classified; collecting the mechanical component state parameter data, electrical component state parameter data and operation state parameter data of the elevators to be classified in real time according to the elevator mechanical component state parameter type matrix, the elevator electrical component state parameter type matrix and the elevator operation state parameter type set, and obtaining the real-time mechanical component state parameter data matrix e1, the real-time electrical component state parameter data matrix e2 and the real-time operation state parameter data set , e 3i Represents the real-time operating status parameter data of the i-th type of the elevator to be classified; e1 and e2 are as follows:

[0049] ; ;

[0050] Among them, e 1ij 、e 2ij State parameter data of the i-th mechanical component type and the j-th electrical component type of the elevator to be classified respectively;

[0051] S42, setting the standard state data of each mechanical component and electrical component of the elevator to be classified and the standard operating state parameter data of each type, obtaining the standard state parameter data matrix e4 of the mechanical component to be classified, the standard state parameter data matrix e5 of the electrical component to be classified and the standard operating state parameter data set to be classified , e 6i Indicates standard operating status parameter data of the i-th type of the elevator to be classified;

[0052] S43, setting a number of historical collection time points to obtain a historical time point set; collecting state parameter data of various mechanical components and electrical components of the elevator to be classified and various operating state parameter data according to the historical time point set to obtain a matrix set of historical mechanical component state parameter data to be classified , the data matrix set of historical electrical component status parameters to be classified And the historical operating status parameter data matrix to be classified ; , respectively represent the mechanical component state parameter data matrix and the electrical component state parameter data matrix of the elevator to be classified at the i-th historical time point, Indicates the total number of historical time points set; , , They are as follows:

[0053] ; ;

[0054] ;

[0055] in, , , They respectively represent the j-th type of state parameter data of the i-th type of mechanical components, the j-th type of state parameter data of the i-th type of electrical components, and the j-th type of operating state parameter data of the elevator to be classified at the k-th historical time point.

[0056] Preferably, the S5 comprises the following steps:

[0057] S51, setting a number of future time points to obtain a future time point set; predicting the state parameters of various mechanical components and electrical components of the elevator to be classified at future moments and various types of operating state parameter data using a BP neural network model according to the future time point set, to obtain a future mechanical component state parameter data matrix set to be classified, a future electrical component state parameter data matrix set to be classified, and a future operating state parameter data matrix to be classified;

[0058] S52, respectively calculating the error degree data between the real-time mechanical component state parameter data matrix, the real-time electrical component state parameter data matrix and the standard state parameter data matrix of the mechanical component to be classified, and the standard state parameter data matrix of the electrical component to be classified, to obtain the real-time mechanical component state parameter error degree data matrix and the real-time electrical component state parameter error degree data matrix; then calculating the error data between the real-time operation state parameter data set and the standard operation state parameter data set to be classified, to obtain the real-time operation state parameter error data;

[0059] S53, respectively calculating the error degree between each future mechanical component state parameter data matrix to be classified in the future mechanical component state parameter data matrix set to be classified and the future electrical component state parameter data matrix set to be classified, as well as the future electrical component state parameter data matrix to be classified and the standard mechanical component state parameter data matrix to be classified, and the standard electrical component state parameter data matrix to be classified, to obtain the future mechanical component state parameter error degree data matrix set to be classified and the future electrical component state parameter error degree data matrix set to be classified; then calculating the error data between each row of the operating state parameter data in the future operating state parameter data matrix to be classified and the standard operating state parameter data set to be classified, to obtain the future operating state parameter error data set to be classified;

[0060] S54. Classify the real-time mechanical component state parameter error degree data matrix, the real-time electrical component state parameter error degree data matrix, the future mechanical component state parameter error degree data matrix set and the future electrical component state parameter error degree data matrix set according to the mechanical component state parameter error clustering center data matrix set, the electrical component state parameter error clustering center data matrix set, the mechanical component state grade set and the electrical component state grade set to obtain real-time mechanical component state grade data, real-time electrical component state grade data, future mechanical component state grade data set and future electrical component state grade data set.

[0061] Preferably, the S6 comprises the following steps:

[0062] S61, setting a mechanical component fault state level threshold, an electrical component fault state level threshold, and an operating state parameter error threshold;

[0063] S62. When the real-time mechanical component status level data is greater than or equal to the mechanical component fault status level threshold, the real-time fault type of the elevator to be classified is determined to be a mechanical fault, otherwise, it is not a mechanical fault; when the real-time electrical component status level data is greater than or equal to the electrical component fault status level threshold, the real-time fault type of the elevator to be classified is determined to be an electrical fault, otherwise, it is not an electrical fault;

[0064] When there is future mechanical component state level data greater than or equal to the mechanical component failure state level threshold in the future mechanical component state level data set, it is determined that the elevator to be classified will have a mechanical failure at a future time and needs mechanical maintenance; otherwise, the elevator to be classified will not have a mechanical failure at a future time; when there is future electrical component state level data greater than or equal to the electrical component failure state level threshold in the future electrical component state level data set, it is determined that the elevator to be classified will have an electrical failure at a future time and needs electrical maintenance; otherwise, the elevator to be classified will not have an electrical failure at a future time;

[0065] A running state parameter error threshold is set; when the real-time running state parameter error data is greater than or equal to the running state parameter error threshold or the future running state parameter error data set to be classified has running state parameter error data greater than or equal to the running state parameter error threshold, it is determined that the elevator to be classified has an operating fault.

[0066] An elevator fault classification system includes an elevator component stage setting module, an elevator state parameter setting module, a historical test state parameter collection module, a historical error degree calculation module, a cluster center calculation module, a level setting module, a to-be-classified elevator state parameter collection module, a prediction module, a to-be-classified error degree data calculation module, a classification module, and a fault determination module.

[0067] The present invention has the following beneficial effects:

[0068] 1. The present invention classifies elevator faults from three aspects: electrical faults, mechanical faults and operational faults; by collecting multiple groups of historical state parameter data of mechanical components and electrical components of the test elevator, clustering these state parameter data, and assigning a grade to each type obtained by clustering, which provides a basis for determining the fault level corresponding to the state parameter data of the mechanical components and electrical components of the elevator to be classified, and then determining the fault category of the elevator to be classified;

[0069] 2. In the present invention, the honey badger optimization algorithm is used to iteratively adjust the multiple cluster center data of the historical mechanical component state parameter error degree data matrix set and the historical electrical component state parameter error degree data matrix set for multiple times, and the overall discrete degree of the historical mechanical component state parameter error degree data matrix set and the historical electrical component state parameter error degree data matrix set is used as the fitness function; therefore, as the iteration proceeds, the discrete degree of the historical mechanical component state parameter error degree data matrix set and the historical electrical component state parameter error degree data matrix set becomes smaller and smaller, indicating that the clustering effect is getting better and better;

[0070] 3. In the present invention, by predicting the state parameter data and operation parameter data of the future mechanical components and electrical components of the elevator to be classified, it is possible to obtain whether the elevator to be classified will fail at a future moment, and timely measures can be taken for maintenance.

[0071] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0072] In order to more clearly illustrate the technical solutions of the embodiments of the invention, the drawings required for describing the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the invention. For ordinary technicians in this field, they can also obtain drawings based on these drawings without paying creative work.

[0073] Figure 1 The present invention is a flowchart of an elevator fault classification method. DETAILED DESCRIPTION

[0074] The following will be combined with the drawings in the embodiments of the invention to clearly and completely describe the technical solutions in the embodiments of the invention. Obviously, the described embodiments are only part of the embodiments of the invention, not all of the embodiments. Based on the embodiments in the invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the invention.

[0075] For example, see Figure 1 , this embodiment is a method for classifying elevator faults, comprising the following steps:

[0076] S1. Set several types of mechanical components, electrical components and state parameter types corresponding to the operation stages to obtain an elevator mechanical component state parameter type matrix, an elevator electrical component state parameter type matrix and an elevator operation state parameter type set;

[0077] The S1 comprises the following steps:

[0078] S11. Set several types of mechanical components, electrical components and operation stages of the elevator to obtain a set of elevator mechanical component types. , Elevator electrical component type set And the elevator operation stage set , a 1i represents the i-th type of mechanical components of the given elevator, Indicates the total number of mechanical component types of the set elevator; a 3i represents the i-th type of electrical components of the set elevator, Indicates the total number of electrical component types of the set elevator; a 21 、a 22 、a 23 、a 24 、a 25 They represent the parking stage, the acceleration stage, the uniform speed stage and the deceleration stage respectively; the elevator mechanical component types include the traction wheel, etc., and the elevator electrical component types include resistors, contactors, etc.;

[0079] S12, setting a number of state parameter types related to elevator operation for each elevator mechanical component type in the elevator mechanical component type set, and obtaining an elevator mechanical component state parameter type matrix ; Then set several state parameter types related to elevator operation for each elevator electrical component type in the elevator electrical component type set to obtain an elevator electrical component state parameter type matrix ; , They are as follows:

[0080] ; ;

[0081] in, represents the state parameter type of the jth type of the i-th elevator mechanical component type in the elevator mechanical component type set, b irepresents the total number of state parameter types of the i-th elevator mechanical component type in the elevator mechanical component type set; represents the state parameter type of the jth type of the i-th elevator electrical component type in the elevator electrical component type set, represents the total number of state parameter types of the i-th elevator electrical component type in the elevator electrical component type set;

[0082] The elevator mechanical component status parameter type matrix includes the wear degree, crack size and deformation degree of the traction wheel, which can be obtained by visual sensors; the elevator electrical component status parameter type matrix includes the resistance value of the resistor, whether it is open circuit, whether the internal contact is poor, and the insulation of the insulating material;

[0083] Then set several state parameter types corresponding to each elevator operation stage in the elevator operation stage set to obtain an elevator operation state parameter type set , Indicates the i-th state parameter type corresponding to each elevator operation stage in the set elevator operation stage set, Indicates the total number of state parameter types corresponding to each elevator operation stage in the set elevator operation stage set;

[0084] The types of elevator operation status parameters include uniform speed, acceleration data, and parking accuracy.

[0085] S2. According to the elevator mechanical component state parameter type matrix and the elevator electrical component state parameter type matrix, the state parameter data of each mechanical component and electrical component in the operation process of several groups of test elevators are collected, and then the error degree data between them and the corresponding standard state parameter data matrix are respectively calculated and clustered to obtain the mechanical component state parameter error cluster center data matrix set and the electrical component state parameter error cluster center data matrix set;

[0086] The S2 comprises the following steps:

[0087] S21, setting a test elevator; collecting several groups of historical state parameter data of each mechanical component and electrical component during the operation of the test elevator according to the elevator mechanical component state parameter type matrix and the elevator electrical component state parameter type matrix, and obtaining a historical mechanical component state parameter data matrix set And the historical electrical component status parameter data matrix set , , They respectively represent the mechanical component state parameter data matrix and the electrical component state parameter data matrix during the k-th historical operation of the test elevator, Indicates the total number of historical running processes of the test elevator collected; sets the standard state parameter data of each mechanical component and electrical component of the test elevator to obtain the historical mechanical component standard state parameter data matrix and historical electrical component standard state parameter data matrix ; , , , They are as follows:

[0088] ; ;

[0089] ; ;

[0090] in, , Respectively , State parameter data of the jth type of the i-th elevator mechanical component type; , Respectively , Standard state parameter data of the jth type of the i-th elevator mechanical component type;

[0091] S22, respectively calculating the error degree data between each historical mechanical component state parameter data matrix in the historical mechanical component state parameter data matrix set and the historical mechanical component standard state parameter data matrix, and the error degree data between each historical electrical component state parameter data matrix in the historical electrical component state parameter data matrix set and the historical electrical component standard state parameter data matrix, to obtain the historical mechanical component state parameter error degree data matrix set. And the historical electrical component state parameter error degree data matrix set , , The data matrices respectively represent the error degree data matrices between the mechanical component state parameter data matrix and the electrical component state parameter data matrix during the k-th historical operation of the test elevator and the corresponding standard state parameter data matrix; they are as follows:

[0092] ; ;

[0093] in, , Respectively , The error degree between the state parameter data of the jth type of the i-th elevator mechanical component type and the corresponding standard state parameter data; the calculation formulas are as follows:

[0094] ; ;

[0095] S23, clustering the historical mechanical component state parameter error degree data matrix set and the historical electrical component state parameter error degree data matrix set to obtain a mechanical component state parameter error cluster center data matrix set And the electrical component state parameter error cluster center data matrix set , c 1k 、c 2k They respectively represent the kth mechanical component state parameter error cluster center data matrix and the electrical component state parameter error cluster center data matrix obtained by clustering the historical mechanical component state parameter error degree data matrix set and the historical electrical component state parameter error degree data matrix set, , represents the total number of mechanical component state parameter error cluster center data matrices and electrical component state parameter error cluster center data matrices obtained by clustering the historical mechanical component state parameter error degree data matrix set and the historical electrical component state parameter error degree data matrix set; c 1k 、c 2k They are as follows:

[0096] ; ;

[0097] Among them, c 1kij 、c 2kij Respectively represent c 1k 、c 2k The state parameter error data of the i-th elevator mechanical component type and the j-th type of electrical component type.

[0098] The S23 comprises the following steps:

[0099] S231, build component status data cluster center to calculate honey badger population , Indicates that the cluster center of the component status data calculates the i-th honey badger in the honey badger population, Indicates the size of the honey badger population calculated by the cluster center of the component status data; sets the maximum number of iterations for calculating the honey badger population by the cluster center of the component status data to d1 and the current number of iterations to d2, which are recorded as the maximum number of iterations for clustering calculation and the current number of iterations for clustering calculation respectively; the search space dimension for calculating the honey badger population by the cluster center of the component status data is ;

[0100] S232, randomly select a number of historical mechanical component state parameter error degree data matrices and historical electrical component state parameter error degree data matrices from the historical mechanical component state parameter error degree data matrix set and the historical electrical component state parameter error degree data matrix set as component state data clustering centers to calculate the initial position of each honey badger in the honey badger population, and obtain a first initial position matrix set , Indicates the cluster center of the component status data calculation in the honey badger population The initial position matrix of a honey badger is as follows:

[0101] ; ;

[0102] ;

[0103] in, , Respectively Middle A data matrix of cluster centers of errors in state parameters of mechanical components and a data matrix of cluster centers of errors in state parameters of electrical components; , Respectively , State parameter error data of the i-th elevator mechanical component type and the j-th type of electrical component type;

[0104] S233, constructing a component state data clustering center according to the historical mechanical component state parameter error degree data matrix set and the historical electrical component state parameter error degree data matrix set to calculate the first Fitness function of a honey badger ;as follows:

[0105] ;

[0106] In the formula, , They respectively represent the overall discreteness of the historical mechanical component state parameter error degree data matrix set and the historical electrical component state parameter error degree data matrix set; the calculation formulas are as follows:

[0107] ;

[0108] ;

[0109] S234, start iteration, before iteration, set the current iteration number of the cluster calculation to 1; in the first round of iteration, use the cluster center of the component status data to calculate the first Fitness function of a honey badger Calculate the fitness value of the initial position matrix of each honey badger in the first initial position matrix set to obtain a first fitness value set; use the maximum fitness value in the first fitness value set and the corresponding initial position matrix of the honey badger as the first global optimal fitness and the first global optimal position respectively; update the initial position matrix of each honey badger in the first initial position matrix set according to the first global optimal fitness and the first global optimal position; after the update is completed, add 1 to the current iteration number of the cluster calculation and enter the next round of iteration;

[0110] In each other round of iteration, the cluster center of the component status data is used to calculate the first Fitness function of a honey badger Calculate the fitness value of the position matrix of each honey badger in the honey badger population calculated by the cluster center of the component status data updated in the previous iteration process to obtain a second fitness value set; use the maximum fitness value in the second fitness value set and the corresponding position matrix of the honey badger as the second global optimal fitness and the second global optimal position respectively; update the position matrix of each honey badger in the honey badger population calculated by the cluster center of the component status data updated in the previous iteration process according to the second global optimal fitness and the second global optimal position; after the update is completed, add 1 to the current iteration number of the cluster calculation and enter the next iteration;

[0111] S235, when When , the iteration stops, and the data matrix set of the cluster center of the state parameter error of the mechanical component and the data matrix set of the cluster center of the state parameter error of the electrical component are obtained; otherwise, the iteration continues until Until then.

[0112] S3, setting the mechanical component state level and the electrical component state level for the mechanical component state parameter error cluster center data matrix set and the electrical component state parameter error cluster center data matrix set to obtain a mechanical component state level set and an electrical component state level set;

[0113] The S3 comprises the following steps:

[0114] S31, setting a corresponding mechanical component state level and electrical component state level for each state parameter error cluster center data matrix in the mechanical component state parameter error cluster center data matrix set and the electrical component state parameter error cluster center data matrix set, to obtain a mechanical component state level set and electrical component status level sets , , Indicates the set i-th mechanical component status level and electrical component status level; the level values ​​in the mechanical component status level set and the electrical component status level set are 1, 2..., and the higher the level value, the more serious the surface mechanical fault or electrical fault.

[0115] S4. Collecting real-time and historical status parameter data of the elevator to be classified according to the elevator mechanical component status parameter type matrix, the elevator electrical component status parameter type matrix and the elevator operation status parameter type set;

[0116] The S4 comprises the following steps:

[0117] S41, elevator to be classified; according to the elevator mechanical component state parameter type matrix, the elevator electrical component state parameter type matrix and the elevator operation state parameter type set, the mechanical component state parameter data, the electrical component state parameter data and the operation state parameter data of each stage of the elevator to be classified are collected in real time to obtain the real-time mechanical component state parameter data matrix e1, the real-time electrical component state parameter data matrix e2 and the real-time operation state parameter data set , e 3i Represents the real-time operating status parameter data of the i-th type of the elevator to be classified; e1 and e2 are as follows:

[0118] ; ;

[0119] Among them, e 1ij 、e 2ij State parameter data of the i-th mechanical component type and the j-th electrical component type of the elevator to be classified respectively;

[0120] S42, setting the standard state data of each mechanical component and electrical component of the elevator to be classified and the standard operating state parameter data of each type, obtaining the standard state parameter data matrix e4 of the mechanical component to be classified, the standard state parameter data matrix e5 of the electrical component to be classified and the standard operating state parameter data set to be classified , e 6i Indicates standard operating status parameter data of the i-th type of the elevator to be classified;

[0121] S43, setting a number of historical collection time points to obtain a historical time point set; collecting state parameter data of various mechanical components and electrical components of the elevator to be classified and various operating state parameter data according to the historical time point set to obtain a matrix set of historical mechanical component state parameter data to be classified , the data matrix set of historical electrical component status parameters to be classified And the historical operating status parameter data matrix to be classified ; , respectively represent the mechanical component state parameter data matrix and the electrical component state parameter data matrix of the elevator to be classified at the i-th historical time point, Indicates the total number of set historical time points; , , They are as follows:

[0122] ; ;

[0123] ;

[0124] in, , , They respectively represent the j-th type of state parameter data of the i-th type of mechanical components, the j-th type of state parameter data of the i-th type of electrical components, and the j-th type of operating state parameter data of the elevator to be classified at the k-th historical time point.

[0125] S5. Predict the state data at a future time according to the historical state parameter data of the elevator to be classified, and calculate the error degree between the prediction result and the real-time state data of the elevator to be classified and the standard state parameter, and then classify them according to the data matrix set of the cluster center of the mechanical component state parameter error and the data matrix set of the cluster center of the electrical component state parameter error, to obtain the real-time mechanical component state level data, the real-time electrical component state level data, the future mechanical component state level data set and the future electrical component state level data set;

[0126] The S5 comprises the following steps:

[0127] S51, setting a number of future time points to obtain a future time point set; predicting the state parameters of various mechanical components and electrical components of the elevator to be classified at future moments and various types of operating state parameter data using a BP neural network model according to the future time point set, to obtain a future mechanical component state parameter data matrix set to be classified, a future electrical component state parameter data matrix set to be classified, and a future operating state parameter data matrix to be classified;

[0128] S52, respectively calculating the error degree data between the real-time mechanical component state parameter data matrix, the real-time electrical component state parameter data matrix and the standard state parameter data matrix of the mechanical component to be classified, and the standard state parameter data matrix of the electrical component to be classified, to obtain the real-time mechanical component state parameter error degree data matrix and the real-time electrical component state parameter error degree data matrix; then calculating the error data between the real-time operation state parameter data set and the standard operation state parameter data set to be classified, to obtain the real-time operation state parameter error data;

[0129] S53, respectively calculating the error degree between each future mechanical component state parameter data matrix to be classified in the future mechanical component state parameter data matrix set to be classified and the future electrical component state parameter data matrix set to be classified, as well as the future electrical component state parameter data matrix to be classified and the standard mechanical component state parameter data matrix to be classified, and the standard electrical component state parameter data matrix to be classified, to obtain the future mechanical component state parameter error degree data matrix set to be classified and the future electrical component state parameter error degree data matrix set to be classified; then calculating the error data between each row of the operating state parameter data in the future operating state parameter data matrix to be classified and the standard operating state parameter data set to be classified, to obtain the future operating state parameter error data set to be classified;

[0130] S54. Classify the real-time mechanical component state parameter error degree data matrix, the real-time electrical component state parameter error degree data matrix, the future mechanical component state parameter error degree data matrix set and the future electrical component state parameter error degree data matrix set according to the mechanical component state parameter error clustering center data matrix set, the electrical component state parameter error clustering center data matrix set, the mechanical component state grade set and the electrical component state grade set to obtain real-time mechanical component state grade data, real-time electrical component state grade data, future mechanical component state grade data set and future electrical component state grade data set.

[0131] S6. Determine the fault type of the elevator to be classified according to the real-time mechanical component status level data, the real-time electrical component status level data, the future mechanical component status level data set, and the future electrical component status level data set;

[0132] The S6 comprises the following steps:

[0133] S61, setting a mechanical component fault state level threshold, an electrical component fault state level threshold, and an operating state parameter error threshold;

[0134] S62. When the real-time mechanical component status level data is greater than or equal to the mechanical component fault status level threshold, the real-time fault type of the elevator to be classified is determined to be a mechanical fault, otherwise, it is not a mechanical fault; when the real-time electrical component status level data is greater than or equal to the electrical component fault status level threshold, the real-time fault type of the elevator to be classified is determined to be an electrical fault, otherwise, it is not an electrical fault;

[0135] When there is future mechanical component state level data greater than or equal to the mechanical component failure state level threshold in the future mechanical component state level data set, it is determined that the elevator to be classified will have a mechanical failure at a future time and needs mechanical maintenance; otherwise, the elevator to be classified will not have a mechanical failure at a future time; when there is future electrical component state level data greater than or equal to the electrical component failure state level threshold in the future electrical component state level data set, it is determined that the elevator to be classified will have an electrical failure at a future time and needs electrical maintenance; otherwise, the elevator to be classified will not have an electrical failure at a future time;

[0136] A running state parameter error threshold is set; when the real-time running state parameter error data is greater than or equal to the running state parameter error threshold or the future running state parameter error data set to be classified has running state parameter error data greater than or equal to the running state parameter error threshold, it is determined that the elevator to be classified has an operating fault.

[0137] Embodiment 2: This embodiment discloses an elevator fault classification system, which can implement the method of the above embodiment, including an elevator component stage setting module, an elevator state parameter setting module, a historical test state parameter collection module, a historical error degree calculation module, a cluster center calculation module, a level setting module, a to-be-classified elevator state parameter collection module, a prediction module, a to-be-classified error degree data calculation module, a classification module, and a fault determination module;

[0138] The elevator component stage setting module is used to set several types of mechanical components, electrical components and operation stages of the elevator, and obtain an elevator mechanical component type set, an elevator electrical component type set and an elevator operation stage set;

[0139] The elevator state parameter setting module is used to set the state parameter types corresponding to the elevator mechanical component type set, the elevator electrical component type set and the elevator operation stage set, and obtain the elevator mechanical component state parameter type matrix, the elevator electrical component state parameter type matrix and the elevator operation state parameter type set;

[0140] The historical test state parameter acquisition module is used to collect state parameter data of each mechanical component and electrical component in several groups of historical operation processes of the test elevator according to the elevator mechanical component state parameter type matrix and the elevator electrical component state parameter type matrix, and obtain a historical mechanical component state parameter data matrix set and a historical electrical component state parameter data matrix set;

[0141] The historical error degree calculation module is used to calculate the error degree data between the historical mechanical component state parameter data matrix set and the historical electrical component state parameter data matrix set and the corresponding standard state parameter data matrix, and obtain the historical mechanical component state parameter error degree data matrix set and the historical electrical component state parameter error degree data matrix set;

[0142] The cluster center calculation module is used to perform clustering operations on the historical mechanical component state parameter error degree data matrix set and the historical electrical component state parameter error degree data matrix set to obtain a mechanical component state parameter error cluster center data matrix set and an electrical component state parameter error cluster center data matrix set;

[0143] The level setting module is used to set the mechanical component state level and the electrical component state level for the mechanical component state parameter error cluster center data matrix set and the electrical component state parameter error cluster center data matrix set to obtain a mechanical component state level set and an electrical component state level set;

[0144] The elevator state parameter collection module to be classified is used to collect real-time and historical state parameter data to be classified according to the elevator mechanical component state parameter type matrix, the elevator electrical component state parameter type matrix and the elevator operation state parameter type set, and obtain a real-time mechanical component state parameter data matrix, a real-time electrical component state parameter data matrix, a real-time operation state parameter data set, a historical mechanical component state parameter data matrix set to be classified, a historical electrical component state parameter data matrix set to be classified and a historical operation state parameter data matrix to be classified;

[0145] The prediction module is used to predict the state data at the future time according to the historical mechanical component state parameter data matrix set to be classified, the historical electrical component state parameter data matrix set to be classified, and the historical operation state parameter data matrix to be classified, so as to obtain the future mechanical component state parameter data matrix set to be classified, the future electrical component state parameter data matrix set to be classified, and the future operation state parameter data matrix to be classified;

[0146] The to-be-classified error degree data calculation module is used to calculate the error degree between the state parameters of the to-be-classified elevators obtained by the collection and the standard state parameters, and obtain a real-time mechanical component state parameter error degree data matrix, a real-time electrical component state parameter error degree data matrix, real-time operation state parameter error data, a future mechanical component state parameter error degree data matrix set to be classified, a future electrical component state parameter error degree data matrix set to be classified, and a future operation state parameter error data set to be classified;

[0147] The classification module is used to classify the real-time mechanical component state parameter error degree data matrix, the real-time electrical component state parameter error degree data matrix, the real-time operation state parameter error data, the future mechanical component state parameter error degree data matrix set to be classified, the future electrical component state parameter error degree data matrix set to be classified, and the future operation state parameter error data set to be classified according to the mechanical component state parameter error cluster center data matrix set and the electrical component state parameter error cluster center data matrix set, so as to obtain the real-time mechanical component state level data, the real-time electrical component state level data, the future mechanical component state level data set, and the future electrical component state level data set;

[0148] The fault determination module is used to determine the fault type of the elevator to be classified according to the real-time mechanical component status level data, the real-time electrical component status level data, the future mechanical component status level data set and the future electrical component status level data set.

[0149] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0150] The preferred embodiments of the invention disclosed above are only used to help explain the invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to the specific implementation methods described. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the invention, so that those skilled in the art can understand and use the invention well.

Claims

1. A method for classifying elevator faults, characterized in that: The following steps are involved: S1. Set several types of mechanical components, electrical components and state parameter types corresponding to the operation stages to obtain an elevator mechanical component state parameter type matrix, an elevator electrical component state parameter type matrix and an elevator operation state parameter type set; S2. According to the elevator mechanical component state parameter type matrix and the elevator electrical component state parameter type matrix, the state parameter data of each mechanical component and electrical component in the operation process of several groups of test elevators are collected, and then the error degree data between them and the corresponding standard state parameter data matrix are respectively calculated and clustered to obtain the mechanical component state parameter error cluster center data matrix set and the electrical component state parameter error cluster center data matrix set; S3, setting the mechanical component state level and the electrical component state level for the mechanical component state parameter error cluster center data matrix set and the electrical component state parameter error cluster center data matrix set to obtain a mechanical component state level set and an electrical component state level set; S4. Collecting real-time and historical status parameter data of the elevator to be classified according to the elevator mechanical component status parameter type matrix, the elevator electrical component status parameter type matrix and the elevator operation status parameter type set; S5. Predict the state data at a future time according to the historical state parameter data of the elevator to be classified, and calculate the error degree between the prediction result and the real-time state data of the elevator to be classified and the standard state parameter, and then classify them according to the data matrix set of the cluster center of the mechanical component state parameter error and the data matrix set of the cluster center of the electrical component state parameter error, to obtain the real-time mechanical component state level data, the real-time electrical component state level data, the future mechanical component state level data set and the future electrical component state level data set; S6. Determine the fault type of the elevator to be classified according to the real-time mechanical component status level data, the real-time electrical component status level data, the future mechanical component status level data set, and the future electrical component status level data set.

2. An elevator fault classification method according to claim 1, characterized in that: The S1 comprises the following steps: S11. Setting several types of mechanical components, electrical components and operation stages of the elevator to obtain an elevator mechanical component type set, an elevator electrical component type set and an elevator operation stage set; S12, setting a number of state parameter types related to elevator operation for each elevator mechanical component type in the elevator mechanical component type set to obtain an elevator mechanical component state parameter type matrix; and then setting a number of state parameter types related to elevator operation for each elevator electrical component type in the elevator electrical component type set to obtain an elevator electrical component state parameter type matrix; Then, a plurality of state parameter types corresponding to each elevator operation stage in the elevator operation stage set are set to obtain an elevator operation state parameter type set.

3. An elevator fault classification method according to claim 2, characterized in that: The S2 comprises the following steps: S21, setting a test elevator; collecting several groups of historical state parameter data of each mechanical component and electrical component in the test elevator's operation process according to the elevator mechanical component state parameter type matrix and the elevator electrical component state parameter type matrix, and obtaining a historical mechanical component state parameter data matrix set and a historical electrical component state parameter data matrix set; setting standard state parameter data of each mechanical component and electrical component of the test elevator, and obtaining a historical mechanical component standard state parameter data matrix and a historical electrical component standard state parameter data matrix; S22, respectively calculating the error degree data between each historical mechanical component state parameter data matrix in the historical mechanical component state parameter data matrix set and the historical mechanical component standard state parameter data matrix, and the error degree data between each historical electrical component state parameter data matrix in the historical electrical component state parameter data matrix set and the historical electrical component standard state parameter data matrix, to obtain a historical mechanical component state parameter error degree data matrix set and a historical electrical component state parameter error degree data matrix set; S23, clustering the historical mechanical component state parameter error degree data matrix set and the historical electrical component state parameter error degree data matrix set to obtain a mechanical component state parameter error cluster center data matrix set and an electrical component state parameter error cluster center data matrix set.

4. An elevator fault classification method according to claim 3, characterized in that: The S23 comprises the following steps: S231, constructing a cluster center of component status data to calculate the honey badger population; setting the maximum number of iterations of the cluster center of component status data to calculate the honey badger population to d1 and the current number of iterations to d2, which are recorded as the maximum number of iterations of cluster calculation and the current number of iterations of cluster calculation respectively; S232, randomly selecting a number of historical mechanical component state parameter error degree data matrices and historical electrical component state parameter error degree data matrices from the historical mechanical component state parameter error degree data matrix set and the historical electrical component state parameter error degree data matrix set as component state data clustering centers to calculate the initial position of each honey badger in the honey badger population, and obtaining a first initial position matrix set; S233, constructing a component state data clustering center according to the historical mechanical component state parameter error degree data matrix set and the historical electrical component state parameter error degree data matrix set to calculate the first The fitness function of a honey badger; S234, start iteration; in each round of iteration, use the cluster center of the component status data to calculate the first The fitness function of each honey badger calculates the component status data cluster center updated in the previous iteration process, calculates the fitness value of the position matrix of each honey badger in the honey badger population, and updates the component status data cluster center updated in the previous iteration process to calculate the position matrix of each honey badger in the honey badger population; S235, when When , the iteration stops, and the data matrix set of the cluster center of the state parameter error of the mechanical component and the data matrix set of the cluster center of the state parameter error of the electrical component are obtained; otherwise, the iteration continues until Until then.

5. An elevator fault classification method according to claim 4, characterized in that: The S3 comprises the following steps: S31. Set a corresponding mechanical component state level and electrical component state level for each state parameter error cluster center data matrix in the mechanical component state parameter error cluster center data matrix set and the electrical component state parameter error cluster center data matrix set to obtain a mechanical component state level set and an electrical component state level set.

6. An elevator fault classification method according to claim 5, characterized in that: The S4 comprises the following steps: S41, elevators to be classified; collecting the mechanical component state parameter data, electrical component state parameter data and operation state parameter data of the elevators to be classified in real time according to the elevator mechanical component state parameter type matrix, the elevator electrical component state parameter type matrix and the elevator operation state parameter type set, and obtaining a real-time mechanical component state parameter data matrix, a real-time electrical component state parameter data matrix and a real-time operation state parameter data set; S42, setting the standard state data of each mechanical component and electrical component of the elevator to be classified and the standard operating state parameter data of each type, to obtain a standard state parameter data matrix of the mechanical component to be classified, a standard state parameter data matrix of the electrical component to be classified and a standard operating state parameter data set to be classified; S43. Set a number of historical collection time points to obtain a historical time point set; collect state parameter data of various mechanical components and electrical components of the elevator to be classified and various operating state parameter data according to the historical time point set to obtain a historical mechanical component state parameter data matrix set to be classified, a historical electrical component state parameter data matrix set to be classified and a historical operating state parameter data matrix to be classified.

7. An elevator fault classification method according to claim 6, characterized in that: The S5 comprises the following steps: S51, setting a number of future time points to obtain a future time point set; predicting the state parameters of various mechanical components and electrical components of the elevator to be classified at future moments and various types of operating state parameter data using a BP neural network model according to the future time point set, to obtain a future mechanical component state parameter data matrix set to be classified, a future electrical component state parameter data matrix set to be classified, and a future operating state parameter data matrix to be classified; S52, respectively calculating the error degree data between the real-time mechanical component state parameter data matrix, the real-time electrical component state parameter data matrix and the standard state parameter data matrix of the mechanical component to be classified, and the standard state parameter data matrix of the electrical component to be classified, to obtain the real-time mechanical component state parameter error degree data matrix and the real-time electrical component state parameter error degree data matrix; then calculating the error data between the real-time operation state parameter data set and the standard operation state parameter data set to be classified, to obtain the real-time operation state parameter error data; S53, respectively calculating the error degree between each future mechanical component state parameter data matrix to be classified in the future mechanical component state parameter data matrix set to be classified and the future electrical component state parameter data matrix set to be classified, as well as the future electrical component state parameter data matrix to be classified and the standard mechanical component state parameter data matrix to be classified, and the standard electrical component state parameter data matrix to be classified, to obtain the future mechanical component state parameter error degree data matrix set to be classified and the future electrical component state parameter error degree data matrix set to be classified; then calculating the error data between each row of the operating state parameter data in the future operating state parameter data matrix to be classified and the standard operating state parameter data set to be classified, to obtain the future operating state parameter error data set to be classified; S54. Classify the real-time mechanical component state parameter error degree data matrix, the real-time electrical component state parameter error degree data matrix, the future mechanical component state parameter error degree data matrix set and the future electrical component state parameter error degree data matrix set according to the mechanical component state parameter error clustering center data matrix set, the electrical component state parameter error clustering center data matrix set, the mechanical component state grade set and the electrical component state grade set to obtain real-time mechanical component state grade data, real-time electrical component state grade data, future mechanical component state grade data set and future electrical component state grade data set.

8. An elevator fault classification method according to claim 7, characterized in that: The S6 comprises the following steps: S61, setting a mechanical component fault state level threshold, an electrical component fault state level threshold, and an operating state parameter error threshold; S62. When the real-time mechanical component status level data is greater than or equal to the mechanical component fault status level threshold, the real-time fault type of the elevator to be classified is determined to be a mechanical fault, otherwise, it is not a mechanical fault; when the real-time electrical component status level data is greater than or equal to the electrical component fault status level threshold, the real-time fault type of the elevator to be classified is determined to be an electrical fault, otherwise, it is not an electrical fault; When there is future mechanical component state level data greater than or equal to the mechanical component failure state level threshold in the future mechanical component state level data set, it is determined that the elevator to be classified will have a mechanical failure at a future time and needs mechanical maintenance; otherwise, the elevator to be classified will not have a mechanical failure at a future time; when there is future electrical component state level data greater than or equal to the electrical component failure state level threshold in the future electrical component state level data set, it is determined that the elevator to be classified will have an electrical failure at a future time and needs electrical maintenance; otherwise, the elevator to be classified will not have an electrical failure at a future time; A running state parameter error threshold is set; when the real-time running state parameter error data is greater than or equal to the running state parameter error threshold or the future running state parameter error data set to be classified has running state parameter error data greater than or equal to the running state parameter error threshold, it is determined that the elevator to be classified has an operating fault.

9. A system for implementing an elevator fault classification method as claimed in any one of claims 1 to 8.

Images