Heterogeneous elevator fault detection method and system based on deep reinforcement learning algorithm

Abstract

The invention relates to a heterogeneous elevator fault detection method and system based on a deep reinforcement learning algorithm, and the method comprises the steps: obtaining elevator operation data, extracting a corresponding operation characteristic variable, carrying out the data format conversion of the operation characteristic variable through combining the operation time of an elevator, obtaining the operation characteristic data of a unified data format, and carrying out the fault detection of the elevator. Under the same elevator running time, the variable incidence relation between the related running characteristic data is analyzed, a fault prediction model of the heterogeneous elevator is constructed, fault characteristic variables and corresponding fault running states when the elevator is abnormal are obtained, the fault characteristic variables and the corresponding fault running states are input into the fault prediction model, and the fault prediction model is used for predicting the abnormal elevator running state. The method comprises the following steps: acquiring an elevator fault prediction result, carrying out fault judgment processing on the elevator fault prediction result, and carrying out fault tracing processing on the elevator according to the fault judgment result to obtain fault detection data of the heterogeneous elevator. The method has the effect of improving the fault detection accuracy of the heterogeneous elevators.

Description

Technical Field

[0001] The present invention relates to the technical field of elevator management, and in particular to a heterogeneous elevator fault detection method and system based on a deep reinforcement learning algorithm. Background Art

[0002] At present, with the widespread application of Internet of Things technology in daily life, data collection of running equipment is carried out by combining Internet of Things technology with the technology of equipment operation terminals to realize the operation status detection of running equipment.

[0003] The existing fault detection method for heterogeneous elevators is usually to collect operating data from different monitoring terminals through Internet of Things devices. The data obtained from different monitoring terminals are heterogeneous data with inconsistent formats. Combined with the elevator inspection data of elevator maintenance personnel, the elevator maintenance personnel conduct a manual joint evaluation of the heterogeneous data and the elevator inspection data to obtain the fault detection results of the heterogeneous elevators. However, there are data barriers between the heterogeneous data, and there are large subjective factors in manual fault assessment alone. The accuracy of fault detection is affected by human experience. There is room for further optimization of the fault detection method for heterogeneous elevators. Summary of the invention

[0004] In order to improve the fault detection accuracy of heterogeneous elevators, the present application provides a heterogeneous elevator fault detection method and system based on a deep reinforcement learning algorithm.

[0005] In the first aspect, the above-mentioned invention objective of the present application is achieved through the following technical solutions:

[0006] A heterogeneous elevator fault detection method based on deep reinforcement learning algorithm, comprising:

[0007] Acquire elevator operation data and extract corresponding operation characteristic variables, and convert the operation characteristic variables into data formats in combination with the elevator operation time to obtain operation characteristic data in a unified data format;

[0008] Under the same elevator operation time, the variable correlation between related operation characteristic data is analyzed, and a fault prediction model for heterogeneous elevators is constructed;

[0009] Acquire fault characteristic variables and corresponding fault operation states when the elevator is abnormal, input the fault characteristic variables and corresponding fault operation states into the fault prediction model, and obtain the elevator fault prediction result;

[0010] A fault determination process is performed on the elevator fault prediction result, and a fault source tracing process is performed on the elevator according to the fault determination result to obtain fault detection data of the heterogeneous elevator.

[0011] In a preferred example, the present application can be further configured as follows: analyzing the variable association relationship between the relevant operation characteristic data under the same elevator operation time, and constructing a fault prediction model for heterogeneous elevators, specifically including:

[0012] Under the same elevator running time, obtain the elevator stop position and the target floor height in the corresponding moving direction, and analyze the running speed between the elevator stop position and the next target floor;

[0013] The variable association relationship between the elevator-related operation characteristic data is expressed by formula (1), which is as follows:

[0014]

[0015] Among them, E(v, h) represents the elevator variable correlation function, a i represents the acceleration bias of the elevator's i-th move, v i represents the running speed of the elevator for the i-th movement, n represents the number of movements between the elevator location and the target stop floor, and h j represents the operating altitude of the jth operation, b j Indicates the elevator operating height h j The corresponding gravity acceleration bias, m represents the number of times the elevator running height changes in the same running direction, ω ij represents the association weight between the jth target floor height and the running rate of the i-th run;

[0016] According to the variable association relationship, the j-th target floor height h is calculated by formula (2): j The activation probability of , formula (2) is as follows:

[0017]

[0018] The running rate v of the i-th run is calculated by formula (3): i The activation probability of is given by formula (3):

[0019]

[0020] According to the variable association relationship and the operation rate activation probability and the target floor height activation probability of the corresponding variables, a fault prediction model for heterogeneous elevators is constructed.

[0021] In a preferred example, the present application can be further configured as follows: the fault characteristic variables and the corresponding fault operation status when the elevator is abnormal are obtained, and the fault characteristic variables and the corresponding fault operation status are input into the fault prediction model to obtain the elevator fault prediction result, specifically including:

[0022] Obtain the number of operating floors when the elevator is abnormal and analyze the changes in operating variables between adjacent operating floors of the elevator to obtain the abnormal fault characteristic variables of the elevator and the corresponding fault operating status;

[0023] The fault operating state and the fault characteristic variables are input into the fault prediction model, the fault occurrence probability corresponding to the fault characteristic variables is analyzed, and the elevator fault prediction result is obtained.

[0024] In a preferred example, the present application can be further configured as follows: the fault operation state and the fault characteristic variable are input into the fault prediction model, the fault occurrence probability corresponding to the fault characteristic variable is analyzed, and the elevator fault prediction result is obtained, specifically including:

[0025] The fault occurrence probability corresponding to the fault characteristic variable is calculated by formula (4), which is as follows:

[0026]

[0027] Among them, P G represents the probability of failure corresponding to the fault characteristic variable, Δh represents the abnormal running height and normal running height of the elevator h i The running mileage difference between them, Δv represents the abnormal running speed and the normal running speed v of the elevator i The running speed difference between the two, ΔD represents the difference between the elevator fault characteristic variables except the running height and running speed and the normal running variables D i The difference between the variables, P(v i =1|h i )、P(h j =1|v i ) represent the activation probability of the operating height and the activation probability of the operating speed, respectively. E(v i ,h i ) represents the variable association function.

[0028] In a preferred example, the present application can be further configured as follows: performing fault determination processing on the elevator fault prediction result, performing fault tracing processing on the elevator according to the fault determination result, and obtaining fault detection data of heterogeneous elevators, specifically including:

[0029] The elevator fault prediction result is judged by formula (5), and formula (5) is as follows:

[0030]

[0031] Among them, ω i ,ω j They represent the elevator running speed weight and the elevator running height weight respectively, and H represents the maximum running height of the elevator;

[0032] When the fault judgment condition is not met, an elevator stacking structure is constructed in combination with the number of operating floors, and the fault feature variables are input into the elevator stacking structure to trace the fault features to obtain fault detection data of heterogeneous elevators.

[0033] By adopting the above technical scheme, various heterogeneous data such as elevator operating current, operating speed, operating mileage, and passenger and cargo loading conditions in the elevator cargo compartment are obtained during the operation of the elevator, and the data format is converted into a unified data format, which is convenient for unified processing of elevator heterogeneous data. A fault prediction model is constructed in combination with the variable association relationship between the operating characteristic data, which is helpful for faster and more convenient fault prediction management of heterogeneous elevators. The elevator fault prediction results are obtained and fault judgment processing is performed in combination with the fault characteristic variables and the corresponding fault operating status when abnormal operation occurs, which is helpful for verifying the prediction accuracy of the elevator fault prediction results. The elevator stacking structure is constructed in combination with the number of elevator operating floors, and the fault characteristic variables are processed for fault tracing to obtain the fault location of the heterogeneous elevator, thereby obtaining the fault detection data of the heterogeneous elevator, which is helpful for improving the fault detection accuracy of the heterogeneous elevator.

[0034] In the second aspect, the above invention objective of the present application is achieved through the following technical solutions:

[0035] A heterogeneous elevator fault detection system based on deep reinforcement learning algorithm, comprising:

[0036] A data acquisition module is used to acquire elevator operation data and extract corresponding operation characteristic variables, and convert the operation characteristic variables into data formats in combination with the elevator operation time to obtain operation characteristic data in a unified data format;

[0037] The model building module is used to analyze the variable association relationship between the relevant operation characteristic data under the same elevator operation time and build a fault prediction model for heterogeneous elevators;

[0038] A fault prediction module is used to obtain fault characteristic variables and corresponding fault operation states when the elevator is abnormal, and input the fault characteristic variables and corresponding fault operation states into the fault prediction model to obtain the elevator fault prediction result;

[0039] The fault tracing module is used to perform fault determination processing on the elevator fault prediction result, and perform fault tracing processing on the elevator according to the fault determination result to obtain fault detection data of the heterogeneous elevator.

[0040] By adopting the above technical scheme, various heterogeneous data such as elevator operating current, operating speed, operating mileage, and passenger and cargo loading conditions in the elevator cargo compartment are obtained during the operation of the elevator, and the data format is converted into a unified data format, which is convenient for unified processing of elevator heterogeneous data. A fault prediction model is constructed in combination with the variable association relationship between the operating characteristic data, which is helpful for faster and more convenient fault prediction management of heterogeneous elevators. The elevator fault prediction results are obtained and fault judgment processing is performed in combination with the fault characteristic variables and the corresponding fault operating status when abnormal operation occurs, which is helpful for verifying the prediction accuracy of the elevator fault prediction results. The elevator stacking structure is constructed in combination with the number of elevator operating floors, and the fault characteristic variables are processed for fault tracing to obtain the fault location of the heterogeneous elevator, thereby obtaining the fault detection data of the heterogeneous elevator, which is helpful for improving the fault detection accuracy of the heterogeneous elevator.

[0041] On the third aspect, the above-mentioned purpose of the present application is achieved through the following technical solutions:

[0042] A computer device comprises a memory, a processor and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the above-mentioned heterogeneous elevator fault detection method based on deep reinforcement learning algorithm are implemented.

[0043] Fourthly, the above-mentioned purpose of the present application is achieved through the following technical solutions:

[0044] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the above-mentioned heterogeneous elevator fault detection method based on a deep reinforcement learning algorithm.

[0045] In summary, the present application includes at least one of the following beneficial technical effects:

[0046] During the operation of the elevator, various heterogeneous data such as the elevator operating current, operating speed, operating mileage, and the passenger and cargo loading conditions in the elevator cargo compartment are obtained and converted into a unified data format through data format, so as to facilitate unified processing of the elevator heterogeneous data. A fault prediction model is constructed in combination with the variable association relationship between the operating characteristic data, which is helpful to more quickly and conveniently perform fault prediction management on heterogeneous elevators. The elevator fault prediction results are obtained and fault judgment processing is performed in combination with the fault characteristic variables and the corresponding fault operating status when the operation abnormality occurs, which is helpful to verify the prediction accuracy of the elevator fault prediction results. The elevator stacking structure is constructed in combination with the number of elevator operating floors, and the fault characteristic variables are processed for fault tracing to obtain the fault location of the heterogeneous elevator, thereby obtaining the fault detection data of the heterogeneous elevator, which is helpful to improve the fault detection accuracy of the heterogeneous elevator. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 This is a flow chart of an implementation of a heterogeneous elevator fault detection method based on a deep reinforcement learning algorithm in this embodiment.

[0048] Figure 2 This is a structural block diagram of a heterogeneous elevator fault detection system based on a deep reinforcement learning algorithm in this embodiment.

[0049] Figure 3 It is a schematic diagram of the internal structure of a computer device used to implement a heterogeneous elevator fault detection method. DETAILED DESCRIPTION

[0050] The present application is further described in detail below in conjunction with the accompanying drawings.

[0051] In one embodiment, if Figure 1 As shown, the present application discloses a heterogeneous elevator fault detection method based on a deep reinforcement learning algorithm, which specifically includes the following steps:

[0052] S10: Acquire elevator operation data and extract corresponding operation characteristic variables, convert the operation characteristic variables into data formats in combination with the elevator operation time, and obtain operation characteristic data in a unified data format.

[0053] Specifically, according to the preset detection equipment, the image information of the passengers and cargo during the operation of the elevator, the operating information such as the current, speed, mileage of the elevator, the height information such as the elevator operating height and the stop floor height are collected, and the corresponding operating characteristic variables are extracted, such as performing image processing on the image of the passengers and cargo to obtain the actual load variable of the elevator, performing feature extraction on the operating information such as the current, speed, mileage of the elevator to obtain the elevator operating variables, and combining with the elevator operating time, performing data conversion on all the operating characteristic variables under the same operating time, such as a data format with time as the prefix + characteristic variable as the suffix, so as to obtain the operating characteristic data in a unified data format.

[0054] S20: Under the same elevator operation time, analyze the variable correlation relationship between related operation characteristic data, and build a fault prediction model for heterogeneous elevators.

[0055] Specifically, taking the elevator running time as the association point, all the running characteristic data of the same elevator running time are data-associated, and the elevator running time is sequentially associated, so as to obtain the variable association relationship between the running characteristic data, wherein the construction of the fault prediction model specifically includes:

[0056] S201: Under the same elevator running time, the elevator stop position and the target floor height in the corresponding moving direction are obtained, and the running speed between the elevator stop position and the next target floor is analyzed.

[0057] Specifically, under the same elevator running time, the elevator stop position is obtained. If it stops running at a certain place for more than a preset time, it is judged as a stop, and the target floor height corresponding to the moving direction, such as moving downward or upward, is obtained. The target floor height is calculated by the distance between the floor pressed by the people inside the elevator and the current stop position. Combined with the current load of the elevator and the preset acceleration, the running speed between the elevator stop position and the next target floor is calculated.

[0058] S202: The variable association relationship between the elevator-related operation characteristic data is expressed by formula (1), and formula (1) is as follows:

[0059]

[0060] Among them, E(v,h) represents the elevator variable correlation function, a i represents the acceleration bias of the elevator's i-th move, v i represents the running speed of the elevator for the i-th movement, n represents the number of movements between the elevator location and the target stop floor, and h j represents the operating altitude of the jth operation, b j Indicates the elevator operating height h j The corresponding gravity acceleration bias, m represents the number of times the elevator running height changes in the same running direction, ω ij represents the association weight between the j-th target floor height and the running rate of the i-th run.

[0061] S203: Calculate the jth target floor height h according to the variable association relationship using formula (2): j The activation probability of is given by formula (2):

[0062]

[0063] The running rate v of the i-th run is calculated by formula (3): i The activation probability of is given by formula (3):

[0064]

[0065] S204: Construct a fault prediction model for heterogeneous elevators according to the variable association relationship and the activation probability of the running speed and the activation probability of the target floor height of the corresponding variables.

[0066] Specifically, the elevator association relationship is data-associated with the operating rate activation probability and the target floor height activation probability of the corresponding variables, and a fault prediction model for heterogeneous elevators is constructed based on the associated data structure.

[0067] S30: Obtain fault characteristic variables and corresponding fault operating states when the elevator is abnormal, input the fault characteristic variables and the corresponding fault operating states into a fault prediction model, and obtain an elevator fault prediction result.

[0068] Specifically, step S30 includes:

[0069] S301: Obtain the number of operating floors when the elevator is abnormal and analyze the changes in operating variables between adjacent operating floors of the elevator to obtain the fault characteristic variables of the elevator abnormality and the corresponding fault operating state.

[0070] Specifically, when the elevator operates abnormally, combined with the number of operating floors when the abnormality occurs, the operating variable changes of the previous operating floor and the next operating floor of the abnormal operating floor are analyzed, such as the changes in elevator operating variables, changes in carrying weight, changes in operating speed, etc., so as to obtain the abnormal fault characteristic variables of the elevator and the corresponding fault operating status. The fault operating status is a parameter change that exceeds the normal operating parameter change range.

[0071] S302: Inputting the fault operation status and the fault characteristic variables into the fault prediction model, analyzing the fault occurrence probability corresponding to the fault characteristic variables, and obtaining the elevator fault prediction result.

[0072] Specifically, step S302 specifically includes:

[0073] The fault occurrence probability corresponding to the fault characteristic variable is calculated by formula (4), which is as follows:

[0074]

[0075] Among them, P G represents the probability of failure corresponding to the fault characteristic variable, Δh represents the abnormal running height and normal running height of the elevator h i The running mileage difference between them, Δv represents the abnormal running speed and the normal running speed v of the elevator i The running speed difference between the two, ΔD represents the difference between the elevator fault characteristic variables except the running height and running speed and the normal running variables D i The difference between the variables, Ρ(v i =1|h i ), Ρ(h j =1|v i ) represent the activation probability of the operating height and the activation probability of the operating speed, respectively. E(v i ,h i ) represents the variable association function.

[0076] S40: Perform fault determination processing on the elevator fault prediction result, perform fault tracing processing on the elevator according to the fault determination result, and obtain fault detection data of the heterogeneous elevator.

[0077] Specifically, step S40 specifically includes:

[0078] S401: Perform fault judgment on the elevator fault prediction result by formula (5), which is as follows:

[0079]

[0080] Among them, ω i ,ω j They represent the elevator running speed weight and the elevator running height weight respectively, and H represents the maximum running height of the elevator.

[0081] S402: When the fault judgment condition is not met, an elevator stacking structure is constructed in combination with the number of operating floors, and the fault feature variables are input into the elevator stacking structure to trace the fault features to obtain fault detection data of heterogeneous elevators.

[0082] Specifically, when the elevator prediction result does not meet the judgment condition of formula (5), that is, it does not meet the fault judgment condition, the elevator stacking structure is constructed by combining the number of operating floors and the stop probability of each stop floor, and the fault feature variable is input into the elevator stacking structure. The fault feature variable is tracked in reverse until the variable difference of the fault feature variable is the same as the normal operating variable. The corresponding position of the last feature variable difference is taken as the fault source of the fault feature, thereby obtaining the fault detection data of the heterogeneous elevator.

[0083] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0084] In one embodiment, a heterogeneous elevator fault detection system based on a deep reinforcement learning algorithm is provided, and the heterogeneous elevator fault detection system based on a deep reinforcement learning algorithm corresponds one-to-one to the heterogeneous elevator fault detection method based on a deep reinforcement learning algorithm in the above embodiment. Figure 2 As shown in the figure, the heterogeneous elevator fault detection system based on deep reinforcement learning algorithm includes data acquisition module, model building module, fault prediction module and fault tracing module. The detailed description of each functional module is as follows:

[0085] The data acquisition module is used to acquire the elevator operation data and extract the corresponding operation characteristic variables, and convert the operation characteristic variables into data format in combination with the elevator operation time to obtain the operation characteristic data in a unified data format.

[0086] The model building module is used to analyze the variable association relationship between related operating characteristic data under the same elevator operation time and build a fault prediction model for heterogeneous elevators.

[0087] The fault prediction module is used to obtain the fault characteristic variables and the corresponding fault operation status when the elevator is abnormal, input the fault characteristic variables and the corresponding fault operation status into the fault prediction model, and obtain the elevator fault prediction result.

[0088] The fault tracing module is used to perform fault determination processing on the elevator fault prediction results, and to perform fault tracing processing on the elevator according to the fault determination results to obtain fault detection data of heterogeneous elevators.

[0089] Preferably, the model building module specifically includes:

[0090] The variable acquisition submodule is used to obtain the elevator stop position and the target floor height in the corresponding moving direction under the same elevator running time, and analyze the running speed between the elevator stop position and the next target floor.

[0091] The association analysis submodule is used to express the variable association relationship between the elevator-related operation characteristic data through formula (1), and formula (1) is as follows:

[0092]

[0093] Among them, E(v,h) represents the elevator variable correlation function, a i represents the acceleration bias of the elevator's i-th move, v i represents the running speed of the elevator for the i-th movement, n represents the number of movements between the elevator location and the target stop floor, and h j represents the operating altitude of the jth operation, b j Indicates the elevator operating height h j The corresponding gravity acceleration bias, m represents the number of times the elevator running height changes in the same running direction, ω ij represents the association weight between the j-th target floor height and the running rate of the i-th run.

[0094] The height probability calculation submodule is used to calculate the height h of the jth target floor according to the variable association relationship using formula (2) j The activation probability of is given by formula (2):

[0095]

[0096] The rate probability calculation submodule is used to calculate the running rate v of the i-th run through formula (3) i The activation probability of is given by formula (3):

[0097]

[0098] The model building submodule is used to build a fault prediction model for heterogeneous elevators based on the variable association relationship and the activation probability of the operating rate and the target floor height of the corresponding variables.

[0099] Preferably, the fault prediction module specifically includes:

[0100] The abnormal variable acquisition submodule is used to obtain the number of operating floors when the elevator is abnormal and analyze the changes in operating variables between adjacent operating floors of the elevator to obtain the abnormal fault characteristic variables of the elevator and the corresponding fault operating status.

[0101] The fault prediction submodule is used to input the fault operation status and fault characteristic variables into the fault prediction model, analyze the fault occurrence probability corresponding to the fault characteristic variables, and obtain the elevator fault prediction result.

[0102] Preferably, the fault prediction submodule specifically includes:

[0103] The fault occurrence probability corresponding to the fault characteristic variable is calculated by formula (4), which is as follows:

[0104]

[0105] Among them, P G represents the probability of failure corresponding to the fault characteristic variable, Δh represents the abnormal running height and normal running height of the elevator h i The running mileage difference between them, Δv represents the abnormal running speed and the normal running speed v of the elevator i The running speed difference between the two, ΔD represents the difference between the elevator fault characteristic variables except the running height and running speed and the normal running variables D i The difference between the variables, P(v i =1|h i )、P(h j =1|v i ) represent the activation probability of the operating height and the activation probability of the operating speed, respectively. E(v i ,h i ) represents the variable association function.

[0106] Preferably, the fault tracing module specifically includes:

[0107] The fault judgment submodule is used to judge the elevator fault prediction result by formula (5), and formula (5) is as follows:

[0108]

[0109] Among them, ω i ,ω j They represent the elevator running speed weight and the elevator running height weight respectively, and H represents the maximum running height of the elevator.

[0110] The fault tracing submodule is used to construct an elevator stacking structure based on the number of operating floors when the fault judgment conditions are not met, input the fault feature variables into the elevator stacking structure to trace the fault features, and obtain the fault detection data of heterogeneous elevators.

[0111] For the specific limitations of the heterogeneous elevator fault detection system based on the deep reinforcement learning algorithm, please refer to the limitations of the heterogeneous elevator fault detection method based on the deep reinforcement learning algorithm mentioned above, which will not be repeated here. Each module in the above-mentioned heterogeneous elevator fault detection system based on the deep reinforcement learning algorithm can be implemented in whole or in part through software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0112] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 3 As shown. The computer device includes a processor, a memory, a network interface and a database connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data in the process of fault detection of heterogeneous elevators. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a heterogeneous elevator fault detection method based on a deep reinforcement learning algorithm is implemented.

[0113] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of a heterogeneous elevator fault detection method based on a deep reinforcement learning algorithm are implemented.

[0114] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0115] Those skilled in the art will clearly understand that for the sake of convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the system can be divided into different functional units or modules to complete all or part of the functions described above.

[0116] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A heterogeneous elevator fault detection method based on deep reinforcement learning algorithm, characterized in that: include: Acquire elevator operation data and extract corresponding operation characteristic variables, and convert the operation characteristic variables into data formats in combination with the elevator operation time to obtain operation characteristic data in a unified data format; Under the same elevator operation time, the variable correlation between related operation characteristic data is analyzed, and a fault prediction model for heterogeneous elevators is constructed; Acquire fault characteristic variables and corresponding fault operation states when the elevator is abnormal, input the fault characteristic variables and corresponding fault operation states into the fault prediction model, and obtain the elevator fault prediction result; A fault determination process is performed on the elevator fault prediction result, and a fault source tracing process is performed on the elevator according to the fault determination result to obtain fault detection data of the heterogeneous elevator.

2. The heterogeneous elevator fault detection method based on deep reinforcement learning algorithm according to claim 1 is characterized in that: The method of analyzing the variable association relationship between the relevant operation characteristic data under the same elevator operation time and constructing a fault prediction model for heterogeneous elevators specifically includes: Under the same elevator running time, obtain the elevator stop position and the target floor height in the corresponding moving direction, and analyze the running speed between the elevator stop position and the next target floor; The variable association relationship between the elevator-related operation characteristic data is expressed by formula (1), which is as follows: Among them, E(v,h) represents the elevator variable correlation function, a i represents the acceleration bias of the elevator's i-th move, v i represents the running speed of the elevator for the i-th movement, n represents the number of movements between the elevator location and the target stop floor, and h j represents the operating altitude of the jth operation, b j Indicates the elevator operating height h j The corresponding gravity acceleration bias, m represents the number of times the elevator running height changes in the same running direction, ω ij represents the association weight between the jth target floor height and the running rate of the i-th run; According to the variable association relationship, the j-th target floor height h is calculated by formula (2): j The activation probability of , formula (2) is as follows: The running rate v of the i-th run is calculated by formula (3): i The activation probability of is given by formula (3): According to the variable association relationship and the operation rate activation probability and the target floor height activation probability of the corresponding variables, a fault prediction model for heterogeneous elevators is constructed.

3. The heterogeneous elevator fault detection method based on deep reinforcement learning algorithm according to claim 1 is characterized in that: The step of obtaining the fault characteristic variables and the corresponding fault operation status when the elevator is abnormal, inputting the fault characteristic variables and the corresponding fault operation status into the fault prediction model, and obtaining the elevator fault prediction result specifically includes: Obtain the number of operating floors when the elevator is abnormal and analyze the changes in operating variables between adjacent operating floors of the elevator to obtain the abnormal fault characteristic variables of the elevator and the corresponding fault operating status; The fault operating state and the fault characteristic variables are input into the fault prediction model, the fault occurrence probability corresponding to the fault characteristic variables is analyzed, and the elevator fault prediction result is obtained.

4. The heterogeneous elevator fault detection method based on deep reinforcement learning algorithm according to claim 3 is characterized in that: The step of inputting the fault operation state and the fault characteristic variable into the fault prediction model, analyzing the fault occurrence probability corresponding to the fault characteristic variable, and obtaining the elevator fault prediction result specifically includes: The fault occurrence probability corresponding to the fault characteristic variable is calculated by formula (4), which is as follows: Among them, P G represents the probability of failure corresponding to the fault characteristic variable, Δh represents the abnormal running height and normal running height of the elevator h i The running mileage difference between them, Δv represents the abnormal running speed and the normal running speed v of the elevator i The running speed difference between the two, ΔD represents the difference between the elevator fault characteristic variables except the running height and running speed and the normal running variables D i The difference between the variables, Ρ(v i =1|h i ), Ρ(h j =1|v i ) represent the activation probability of the operating height and the activation probability of the operating speed, respectively. E(v i ,h i ) represents the variable association function.

5. The heterogeneous elevator fault detection method based on deep reinforcement learning algorithm according to claim 1 is characterized in that: The performing fault determination processing on the elevator fault prediction result, and performing fault tracing processing on the elevator according to the fault determination result to obtain the fault detection data of the heterogeneous elevator specifically includes: The elevator fault prediction result is judged by formula (5), and formula (5) is as follows: Among them, ω i ,ω j They represent the elevator running speed weight and the elevator running height weight respectively, and H represents the maximum running height of the elevator; When the fault judgment condition is not met, an elevator stacking structure is constructed in combination with the number of operating floors, and the fault feature variables are input into the elevator stacking structure to trace the fault features to obtain fault detection data of heterogeneous elevators.

6. A heterogeneous elevator fault detection system based on deep reinforcement learning algorithm, characterized in that: include: A data acquisition module is used to acquire elevator operation data and extract corresponding operation characteristic variables, and convert the operation characteristic variables into data formats in combination with the elevator operation time to obtain operation characteristic data in a unified data format; The model building module is used to analyze the variable association relationship between the relevant operation characteristic data under the same elevator operation time and build a fault prediction model for heterogeneous elevators; A fault prediction module is used to obtain fault characteristic variables and corresponding fault operation states when the elevator is abnormal, and input the fault characteristic variables and corresponding fault operation states into the fault prediction model to obtain the elevator fault prediction result; The fault tracing module is used to perform fault determination processing on the elevator fault prediction result, and perform fault tracing processing on the elevator according to the fault determination result to obtain fault detection data of the heterogeneous elevator.

7. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the heterogeneous elevator fault detection method based on the deep reinforcement learning algorithm as described in any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the heterogeneous elevator fault detection method based on the deep reinforcement learning algorithm as described in any one of claims 1 to 5 are implemented.

Images