A method and apparatus for servicing a device
By using equipment vibration data for fault prediction and identification code parsing, maintenance data can be automatically obtained for equipment maintenance, solving the problem of low equipment maintenance efficiency and achieving timely maintenance and efficient upkeep.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- 江苏中天互联科技有限公司
- Filing Date
- 2023-01-05
- Publication Date
- 2026-06-26
AI Technical Summary
In existing technologies, equipment failures require manual repair, resulting in low repair efficiency and the inability to repair in a timely manner.
By acquiring equipment vibration data, fault prediction is performed using a pre-built fault prediction model, unique identifiers are parsed to determine service nodes, and target maintenance data is acquired and connected for maintenance.
It improved equipment maintenance efficiency, reduced the risk of human error, and enabled timely equipment maintenance.
Smart Images
Figure CN115953151B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of equipment management systems, and more particularly to an equipment maintenance method and apparatus. Background Technology
[0002] Timely repair of faulty equipment ensures its normal operation and improves its utilization rate. However, current technology often requires maintenance personnel to perform manual repairs only after a malfunction occurs, resulting in low maintenance efficiency and failing to achieve timely repairs.
[0003] There is currently no effective solution to the above problems. Summary of the Invention
[0004] This specification provides an embodiment of a device for equipment maintenance, which can improve the efficiency of equipment maintenance.
[0005] On the one hand, embodiments of this specification provide a method for equipment maintenance, the method comprising:
[0006] The target vibration data of the target device is acquired, and the target vibration data is input into a pre-built fault prediction model to obtain the fault prediction result of the target device. The pre-built fault prediction model is trained based on a first feature vector and a second feature vector, and the first feature vector and the second feature vector are determined by vibration sample data and fault sample data, respectively.
[0007] Determine whether the fault prediction result is less than a preset threshold. If it is determined to be less than the preset threshold, obtain a unique identifier and parse the unique identifier to determine the first service node based on the parsing result.
[0008] A maintenance search request carrying identification information is sent to the first service node, wherein the identification information includes the target device identifier and the maintenance identifier;
[0009] Receive feedback information from the first service node, wherein the feedback information is determined based on the parsing results of the target device identifier and the maintenance identifier;
[0010] Based on the feedback information, determine whether the target maintenance data exists in the first service node;
[0011] When it is determined that target maintenance data exists, it is determined whether the target device has the permission to read the target maintenance data;
[0012] When it is determined that the target device has the permission to read the target maintenance data, the target maintenance data is connected to the target device to perform maintenance on the target device based on the target maintenance data.
[0013] In one embodiment, the pre-built fault prediction model is trained based on a first feature vector and a second feature vector, wherein the first feature vector and the second feature vector are determined by vibration sample data and fault sample data, respectively, including:
[0014] Acquire vibration sample data and fault sample data;
[0015] Based on the vibration sample data, determine the time-frequency image corresponding to the vibration sample data;
[0016] The fault sample data is input into a one-dimensional neural network model to obtain the first feature vector;
[0017] The time-frequency image is input into a two-dimensional neural network model to obtain a second feature vector;
[0018] The target neural network model is trained based on the first feature vector and the second feature vector to obtain a fault prediction model; wherein, the first fully connected layer of the target neural network model is determined by the first fully connected layer in the one-dimensional neural network model and the second fully connected layer in the two-dimensional neural network model.
[0019] In one embodiment, the feedback information is determined based on the parsing results of the target device identifier and the maintenance identifier, including:
[0020] The target device identifier and the maintenance identifier are parsed to obtain target device information and maintenance information;
[0021] The target device information and the maintenance information are associated to obtain associated information;
[0022] Determine the matching information in the first service node that matches the associated information;
[0023] Determine the correlation coefficient between the association information and the matching information;
[0024] Based on the correlation coefficient, the similarity result between the associated information and the matching information is determined;
[0025] The similarity results are used as feedback information.
[0026] In one embodiment, determining whether the target maintenance data is in the first service node based on the feedback information further includes:
[0027] When it is determined that the target maintenance data does not exist in the first service node, the first service node sends a request to the blockchain to retrieve the target maintenance data;
[0028] Based on the acquisition request, the second service node is determined;
[0029] The system receives target maintenance data fed back from the second service node and connects the target maintenance data to the target device to perform maintenance on the target device based on the target maintenance data.
[0030] In one embodiment, determining the second service node based on the acquisition request includes:
[0031] Based on the acquisition request, multiple service nodes are identified;
[0032] Calculate the set of Euclidean distances between multiple service nodes and the target device;
[0033] The Euclidean distances in the Euclidean distance set are compared to obtain the comparison results.
[0034] The target service node corresponding to the minimum value in the comparison processing results is determined as the second service node.
[0035] On the other hand, embodiments of this specification also provide an equipment repair device, which includes:
[0036] The fault prediction module is used to acquire target vibration data of the target device, input the target vibration data into a pre-built fault prediction model, and obtain the fault prediction result of the target device. The pre-built fault prediction model is trained based on a first feature vector and a second feature vector, and the first feature vector and the second feature vector are determined by vibration sample data and fault sample data, respectively.
[0037] The first parsing module is used to determine whether the fault prediction result is less than a preset threshold. When it is determined that the result is less than the preset threshold, a unique identifier is obtained and the unique identifier is parsed to determine the first service node based on the parsing result.
[0038] The second parsing module is used to send a maintenance search request carrying identification information to the first service node, wherein the identification information includes a target device identifier and a maintenance identifier; and to receive feedback information from the first service node, wherein the feedback information is determined based on the parsing results of the target device identifier and the maintenance identifier.
[0039] The first judgment module is used to determine whether the target maintenance data exists in the first service node based on the feedback information.
[0040] The first maintenance module is used to determine whether the target device has the permission to read the target maintenance data when it is determined that the target maintenance data exists; and when it is determined that the target device has the permission to read the target maintenance data, to connect the target maintenance data to the target device so as to perform maintenance on the target device based on the target maintenance data.
[0041] In one embodiment, the apparatus further includes:
[0042] The second judgment module is used to determine the second service node when it is determined that the target maintenance data does not exist in the first service node, and the first service node sends a request to the blockchain to obtain the target maintenance data; and determines the second service node based on the request.
[0043] The second maintenance module is used to receive target maintenance data fed back by the second service node, connect the target maintenance data to the target device, and perform maintenance on the target device based on the target maintenance data.
[0044] This specification also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the above-described device maintenance method.
[0045] Furthermore, embodiments of this specification also provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the aforementioned equipment maintenance method.
[0046] This specification provides an equipment maintenance method and apparatus. First, target vibration data of the target equipment is acquired and input into a pre-built fault prediction model to obtain a fault prediction result for the target equipment. The pre-built fault prediction model is trained based on a first feature vector and a second feature vector, which are determined by vibration sample data and fault sample data, respectively. Second, it is determined whether the fault prediction result is less than a preset threshold. If it is determined to be less than the preset threshold, a unique identifier is acquired and parsed to determine a first service node based on the parsing result. The first service node is then... The service node issues a maintenance search request carrying identification information, including a target device identifier and a maintenance identifier. Further, it receives feedback information from a first service node, which is determined based on the parsing results of the target device identifier and the maintenance identifier. Based on the feedback information, it determines whether target maintenance data exists in the first service node. Finally, if target maintenance data exists, it determines whether the target device has read permission for the target maintenance data. If the target device has read permission, it connects the target maintenance data to the target device to perform maintenance based on the target maintenance data. This solution improves equipment maintenance efficiency and reduces the risk of human error. Attached Figure Description
[0047] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. In the drawings:
[0048] Figure 1 This is a flowchart illustrating one embodiment of a device maintenance method provided in this specification;
[0049] Figure 2 This is a flowchart illustrating another embodiment of a device maintenance method provided in this specification;
[0050] Figure 3 This is a schematic diagram illustrating the structural composition of an equipment maintenance device according to one embodiment of this specification;
[0051] Figure 4 This is a schematic diagram of the structural composition of an equipment maintenance device provided in another embodiment of this specification;
[0052] Figure 5 This is a schematic diagram of the structural composition of an electronic device provided in one embodiment of this specification. Detailed Implementation
[0053] To enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this specification, and not all embodiments. Based on the embodiments in this specification, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of this specification.
[0054] Traditional equipment maintenance methods mostly involve dispatching maintenance personnel to repair equipment after it malfunctions, which fails to achieve timely repairs and is affected by subjective human operation, resulting in reduced equipment maintenance efficiency.
[0055] In view of the above-mentioned problems of existing methods, this application proposes to introduce an equipment maintenance method to improve the efficiency of equipment maintenance and reduce the failure rate of equipment.
[0056] Based on the above ideas, this manual proposes a method for equipment maintenance. First, target vibration data of the target device is acquired and input into a pre-built fault prediction model to obtain a fault prediction result for the target device. The pre-built fault prediction model is trained based on a first feature vector and a second feature vector, which are determined by vibration sample data and fault sample data, respectively. Second, it is determined whether the fault prediction result is less than a preset threshold. If it is determined to be less than the preset threshold, a unique identifier is acquired and parsed to determine a first service node based on the parsing result. A maintenance search request carrying identification information is sent to the first service node, where the identification information includes a target device identifier and a maintenance identifier. Further, feedback information is received from the first service node, where the feedback information is determined based on the parsing result of the target device identifier and the maintenance identifier. Based on the feedback information, it is determined whether target maintenance data exists in the first service node. Finally, if target maintenance data exists, it is determined whether the target device has permission to read the target maintenance data. If the target device has permission to read the target maintenance data, the target maintenance data is connected to the target device to perform maintenance on the target device based on the target maintenance data. The above solutions can improve equipment maintenance efficiency and reduce the risk of human error.
[0057] Figure 1 This is a flowchart illustrating one embodiment of a device maintenance method provided in this specification. While this specification provides method operation steps or apparatus structures as shown in the following embodiments or figures, more or fewer operation steps or module units may be included in the method or apparatus based on conventional or non-inventive effort. In steps or structures where there is no logically necessary causal relationship, the execution order of these steps or the module structure of the apparatus is not limited to the execution order or module structure shown in the embodiments or figures of this specification. When the method or module structure is applied in actual devices, servers, or terminal products, it can be executed sequentially or in parallel according to the method or module structure shown in the embodiments or figures (e.g., in a parallel processor or multi-threaded processing environment, or even in a distributed processing or server cluster implementation environment). For specific implementation, please refer to... Figure 1 As shown, the method may include the following:
[0058] S101: Obtain target vibration data of the target device, input the target vibration data into a pre-built fault prediction model, and obtain the fault prediction result of the target device. The pre-built fault prediction model is obtained by training based on a first feature vector and a second feature vector, and the first feature vector and the second feature vector are determined by vibration sample data and fault sample data, respectively.
[0059] S102: Determine whether the fault prediction result is less than a preset threshold. If it is determined that it is less than the preset threshold, obtain a unique identifier and parse the unique identifier to determine the first service node based on the parsing result.
[0060] S103: Send a maintenance search request carrying identification information to the first service node, wherein the identification information includes the target device identifier and the maintenance identifier.
[0061] S104: Receive feedback information from the first service node, wherein the feedback information is determined based on the parsing results of the target device identifier and the maintenance identifier.
[0062] S105: Based on the feedback information, determine whether the target maintenance data exists in the first service node.
[0063] S106: When it is determined that target maintenance data exists, determine whether the target device has the permission to read the target maintenance data.
[0064] S107: When it is determined that the target device has the permission to read the target maintenance data, the target maintenance data is connected to the target device to perform maintenance on the target device based on the target maintenance data.
[0065] In some embodiments, the target equipment may include at least one of the following: drilling equipment, casting equipment, heat treatment equipment, CNC equipment, and stamping equipment; the target maintenance data may include at least one of the following: maintenance process, cause of failure, replacement parts, and maintenance pictures. The target equipment may be defined by industry associations to ensure that each piece of equipment has a unified standard. Of course, the above is merely illustrative, and the target equipment and target maintenance data are not limited to the examples described above. Those skilled in the art may make other modifications based on the essence of this application, but as long as the functions and effects achieved are the same as or similar to those of this application, they should be covered within the scope of protection of this application.
[0066] In some embodiments, the target vibration data can be data processed by a preprocessing algorithm. The preprocessing algorithm can be an arithmetic mean, a weighted average, a median method, or a fuzzy control method. It should be noted that the preprocessing algorithm is not limited to the examples above. Those skilled in the art may make other changes based on the essence of the technology in this application. However, as long as the function and effect achieved are the same as or similar to those in this application, they should be covered within the scope of protection of this application.
[0067] In some embodiments, the pre-built fault prediction model described above is trained based on a first feature vector and a second feature vector, wherein the first feature vector and the second feature vector are determined by vibration sample data and fault sample data, respectively. In specific implementations, this may include:
[0068] S1: Acquire vibration sample data and fault sample data;
[0069] S2: Determine the time-frequency image corresponding to the vibration sample data based on the vibration sample data;
[0070] S3: Input the fault sample data into a one-dimensional neural network model to obtain the first feature vector;
[0071] S4: Input the time-frequency image into a two-dimensional neural network model to obtain the second feature vector;
[0072] S5: Train the target neural network model based on the first feature vector and the second feature vector to obtain a fault prediction model; wherein, the first fully connected layer of the target neural network model is determined by the first fully connected layer in the one-dimensional neural network model and the second fully connected layer in the two-dimensional neural network model.
[0073] In some embodiments, the above-mentioned fault sample data may include: primary faults and secondary faults, wherein primary faults may include at least one of the following: mechanical faults, electrical faults, water circuit faults, pneumatic faults, hydraulic faults, and lubrication faults; secondary faults may be specific categories derived from primary faults, such as: secondary faults corresponding to mechanical faults may include at least one of the following: gearbox faults, bearing faults, slider faults, and transmission chain faults; secondary faults corresponding to electrical faults may include at least one of the following: CNC system faults, display screen faults, PLC (Programmable Logic Controller) faults, relay faults, push-button switch faults, motor faults, and solenoid valve faults; secondary faults corresponding to pneumatic faults may include at least one of the following: air pump malfunction, drain valve leakage, hose leakage, air gun leakage, metering faults, and cylinder faults; secondary faults corresponding to hydraulic faults may include at least one of the following: oil tank lack, hydraulic pump faults, hydraulic valve faults, oil pipe leakage, and hydraulic system blockage; and secondary faults corresponding to lubrication faults may include at least one of the following: lubrication pump faults, oil pipe leakage, lubrication distributor faults, and lubrication point blockage.
[0074] It should be noted that the aforementioned target equipment exhibits at least one level-one fault. For example, if the target equipment is a drilling device, it may simultaneously exhibit one or more level-one faults, such as simultaneous mechanical and electrical faults, or simultaneous mechanical and lubrication faults. Of course, the above is merely illustrative; the level-one faults present in the target equipment are not limited to the examples described above. Those skilled in the art, inspired by the essence of this application, may make other modifications, but as long as their functions and effects are the same as or similar to those of this application, they should be included within the scope of protection of this application.
[0075] In some embodiments, continuous wavelet transform can be used to convert the vibration data into a two-dimensional time-frequency image, thereby obtaining fault information from the time-frequency two-dimensional plane and enabling local feature analysis of the vibration data in the time or frequency domain. In some embodiments, the fault sample data can be used as input to a one-dimensional neural network model. After passing through the input layer, convolutional layer, pooling layer, and fully connected layer of the one-dimensional neural network model, a set of feature vectors can be obtained as the first feature vector. The time-frequency image can be used as input to a two-dimensional neural network model. After passing through the input layer, convolutional layer, pooling layer, and fully connected layer of the two-dimensional neural network model, another set of feature vectors can be obtained as the second feature vector. These two sets of feature vectors are then concatenated and passed through the convergence layer, fully connected layer, and classification layer of the target neural network model to obtain the fault prediction result. The fully connected layer of the target neural network model can be the sum of the fully connected layers of the one-dimensional neural network model and the two-dimensional neural network model, and the convergence layer can be the sum of the convergence layers of the one-dimensional neural network model and the two-dimensional neural network model. By considering data from different dimensions, the accuracy of fault prediction can be improved.
[0076] In some embodiments, parsing the unique identifier to determine the first service node based on the parsing result includes:
[0077] The unique identifier is parsed to obtain the target parsing address, which is used as the parsing result.
[0078] The service node that matches the parsing result is identified as the first service node.
[0079] In some embodiments, the aforementioned unique identifier can be used to identify service nodes. In specific implementation, the unique identifier can be parsed to obtain the parsing address, and then the service node matching the parsing address can be determined. By parsing the unique identifier, the corresponding service node and the address of the service node can be quickly queried, thereby laying the foundation for timely maintenance of the equipment in the future.
[0080] In some embodiments, the above feedback information is determined based on the parsing results of the target device identifier and the maintenance identifier, and in specific implementations, it may include:
[0081] S1: Parse the target device identifier and the maintenance identifier to obtain target device information and maintenance information;
[0082] S2: Associate the target device information and the maintenance information to obtain associated information;
[0083] S3: Determine the matching information in the first service node that matches the associated information;
[0084] S4: Determine the correlation coefficient between the association information and the matching information;
[0085] S5: Determine the similarity result between the association information and the matching information based on the correlation coefficient;
[0086] S6: Use the similarity results as feedback information.
[0087] In some embodiments, target device information can be obtained by parsing the target device identifier. The target device information may include: device type, function, manufacturer information, etc. Repair information can be obtained by parsing the repair identifier. The repair information may include at least one of the following: repair process, cause of failure, replacement parts, repair pictures. The data such as repair process, cause of failure, replacement parts, and repair pictures can be filled in the device management software, and then the device management software uploads the repair information to the service node according to the standard identifier template. The aforementioned identifier templates can be obtained through industry associations and used to define the format of the target repair data. For example, the data format for the repair process can be defined as: "Field name: RepairProcess Maximum and minimum length Type: String Index 1", where RepairProcess corresponds to the repair process; the data format for the cause of the fault can be defined as: "Field name: Reason Maximum and minimum length Type: String Index 2", where Reason corresponds to the cause of the fault; the data format for replacing parts can be defined as: "Field name: Parts Type: Array (part name, part specification, replacement quantity, replacement location, etc.) Index 3", where Parts corresponds to the parts; the data format for repair images can be defined as: "Field name: Files Type: Array (image number, image URL (Uniform Resource Locator) address, etc.) Index 4", where Files corresponds to the images.
[0088] In some embodiments, device information and maintenance information can be associated to obtain associated information. Matching information matching the associated information in the first service node can be determined using a similarity algorithm, such as determining the correlation coefficient between the associated information and the matching information, and then determining the similarity between the associated information and the matching information based on the value of the correlation coefficient. It should be noted that the above similarity algorithm is not limited to the examples described above. Those skilled in the art may make other modifications based on the essence of this application, such as using locality-sensitive hashing algorithms or minimum hashing algorithms. However, as long as their functions and effects are the same as or similar to those of this application, they should be covered within the scope of protection of this application.
[0089] In some embodiments, the feedback information can be the similarity result, such as: completely similar or completely matched or completely identical, dissimilar or not matched or not identical, not completely similar or not completely matched or not completely identical.
[0090] In some embodiments, see Figure 2 As shown, the above-mentioned determination of whether target maintenance data exists in the first service node based on the feedback information may, in specific implementation, include:
[0091] S201: When it is determined that the target maintenance data does not exist in the first service node, the first service node sends a request to the blockchain to obtain the target maintenance data;
[0092] S202: Determine the second service node based on the acquisition request;
[0093] S203: Receive the target maintenance data fed back by the second service node, connect the target maintenance data to the target device, and perform maintenance on the target device based on the target maintenance data.
[0094] In some embodiments, the presence of target maintenance data in the first service node can be determined by feedback information. For example, if the feedback information is completely similar, completely matched, or completely identical, it is determined that the target maintenance data exists in the first service node; if the feedback information is dissimilar, mismatched, or different, it is determined that the target maintenance data does not exist in the first service node.
[0095] In some embodiments, when it is determined that no maintenance data exists in the first service node, it is necessary to obtain the target maintenance data from other nodes through blockchain technology. For example, the first service node can send a request to the blockchain to obtain the target maintenance data. The blockchain then broadcasts the request to other service nodes. If the target maintenance data exists in other service nodes, they will respond to the request and send the target maintenance data from the other service nodes to the first service node, connecting the target data to the target device for equipment maintenance.
[0096] In some embodiments, the blockchain described above is a distributed, centralized, and trusted storage framework that provides immutable data storage and peer-to-peer, trusted distributed computing. The blockchain adopts a decentralized organizational form; the entire blockchain system has no central node, and all nodes participate equally and jointly maintain a common ledger. Furthermore, it uses a hash-associative chained block structure to store data, ensuring the immutability of on-chain data. A consensus algorithm is employed to achieve trust and collaboration between nodes, and it can accommodate the dynamic joining or leaving of nodes.
[0097] In some embodiments, determining the second service node based on the acquisition request may, in specific implementation, include:
[0098] S1: Based on the acquisition request, determine multiple service nodes;
[0099] S2: Calculate the set of Euclidean distances between multiple service nodes and the target device;
[0100] S3: Compare the Euclidean distances in the Euclidean distance set to obtain the comparison results;
[0101] S4: Determine the target service node corresponding to the minimum value in the comparison processing results, and use it as the second service node.
[0102] In some embodiments, target maintenance data may exist in multiple service nodes. In this case, it is necessary to further determine the optimal service node among these nodes. For example, the Euclidean distances between multiple service nodes and the target device can be calculated, and the minimum Euclidean distance can be determined. The service node corresponding to the minimum Euclidean distance is then selected as the optimal service node. By determining the optimal service node, the efficiency of acquiring maintenance data can be improved, thereby enabling timely maintenance of the equipment.
[0103] In some embodiments, after repairing the target equipment based on the target maintenance data, the specific implementation may further include:
[0104] S1: Determine whether the repair of the target device is completed. If the repair is completed, obtain the storage permission of the target device, and store the target repair data in the target device based on the storage permission.
[0105] S2: When the target equipment experiences a target fault, repair the target equipment based on the target maintenance data.
[0106] In some embodiments, target maintenance data can be stored in the target device so that the target device can be repaired promptly when the target fault occurs again, thereby improving maintenance efficiency. Before storing the target maintenance data in the target device, it is first determined whether the target device has storage permissions. Storing the target maintenance data only when storage permissions are granted enhances the security of maintenance data storage.
[0107] In some embodiments, sharing permissions for the target device can also be obtained to share the target maintenance data stored in the target device with devices that are the same as or similar to the target device, so that when the target device experiences a target fault, the same device and / or similar device can be repaired based on the target maintenance data, thereby improving maintenance efficiency.
[0108] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to interchangeably. Each embodiment focuses on describing the differences from other embodiments. For details, please refer to the foregoing descriptions of the relevant processing embodiments; they will not be repeated here.
[0109] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.
[0110] The above method will be described below with reference to a specific embodiment. However, it is worth noting that this specific embodiment is only for better illustration of this application and does not constitute an improper limitation of this application. Before specific implementation, firstly, vibration sample data and fault sample data are acquired; secondly, based on the vibration sample data, the time-frequency image corresponding to the vibration sample data is determined; the fault sample data is input into a one-dimensional neural network model to obtain a first feature vector; the time-frequency image is input into a two-dimensional neural network model to obtain a second feature vector; finally, the target neural network model is trained based on the first feature vector and the second feature vector to obtain a fault prediction model; wherein, the first fully connected layer of the target neural network model is determined by the first fully connected layer in the one-dimensional neural network model and the second fully connected layer in the two-dimensional neural network model. In specific implementation, firstly, target vibration data of the target device is acquired and input into a pre-constructed fault prediction model to obtain a fault prediction result for the target device. Secondly, it is determined whether the fault prediction result is less than a preset threshold. If it is determined to be less than the preset threshold, a unique identifier is acquired, the unique identifier is parsed to obtain a target parsing address, which is used as the parsing result. A service node matching the parsing result is determined as the first service node. Further, the target device identifier and the maintenance identifier are parsed to obtain target device information and maintenance information. The target device information and the maintenance information are associated to obtain association information. Matching information matching the association information in the first service node is determined. The correlation coefficient between the association information and the matching information is determined. Based on the correlation coefficient, the similarity result between the association information and the matching information is determined. The similarity result is used as feedback information. Further, feedback information from the first service node is received. Based on the feedback information, it is determined whether target maintenance data exists in the first service node. If target maintenance data exists in the first service node, it is determined whether the target device has the permission to read the target maintenance data. Furthermore, when it is determined that the target device has the permission to read the target maintenance data, the target maintenance data is connected to the target device to perform maintenance on the target device based on the target maintenance data. Further, when it is determined that the target maintenance data does not exist in the first service node, the first service node sends a request to the blockchain to obtain the target maintenance data; based on the request, a second service node is determined; the target maintenance data fed back by the second service node is received, and the target maintenance data is connected to the target device to perform maintenance on the target device based on the target maintenance data. Through the above methods, maintenance data can be obtained accurately and quickly, improving equipment maintenance efficiency and saving maintenance costs.
[0111] Based on the same inventive concept, this application also provides an equipment repair apparatus, as described in the following embodiments. Since the principle by which the equipment repair apparatus solves the problem is similar to that of the equipment repair method, the implementation of the equipment repair apparatus can refer to the implementation of the equipment repair method, and repeated details will not be elaborated further. As used below, the terms "unit" or "module" can refer to a combination of software and / or hardware that implements a predetermined function. Although the apparatus described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated. Figure 3 This is a structural block diagram of an equipment repair device according to an embodiment of this application, such as... Figure 3 As shown, it includes: a fault prediction module 301, a first analysis module 302, a second analysis module 303, a first judgment module 304, and a first maintenance module 305. The structure is described below.
[0112] The fault prediction module 301 is used to acquire target vibration data of the target device, input the target vibration data into a pre-built fault prediction model, and obtain the fault prediction result of the target device. The pre-built fault prediction model is trained based on a first feature vector and a second feature vector, and the first feature vector and the second feature vector are determined by vibration sample data and fault sample data, respectively.
[0113] The first parsing module 302 is used to determine whether the fault prediction result is less than a preset threshold. When it is determined that the result is less than the preset threshold, a unique identifier is obtained and the unique identifier is parsed to determine the first service node based on the parsing result.
[0114] The second parsing module 303 is used to send a maintenance search request carrying identification information to the first service node, wherein the identification information includes a target device identifier and a maintenance identifier; and to receive feedback information from the first service node, wherein the feedback information is determined based on the parsing results of the target device identifier and the maintenance identifier.
[0115] The first judgment module 304 is used to determine whether target maintenance data exists in the first service node based on the feedback information;
[0116] The first maintenance module 305 is used to determine whether the target device has the permission to read the target maintenance data when it is determined that the target maintenance data exists; and when it is determined that the target device has the permission to read the target maintenance data, connect the target maintenance data to the target device to perform maintenance on the target device based on the target maintenance data.
[0117] In one embodiment, the fault prediction module 301 may further include: acquiring vibration sample data and fault sample data; determining the time-frequency image corresponding to the vibration sample data based on the vibration sample data; inputting the fault sample data into a one-dimensional neural network model to obtain a first feature vector; inputting the time-frequency image into a two-dimensional neural network model to obtain a second feature vector; training the target neural network model based on the first feature vector and the second feature vector to obtain a fault prediction model; wherein, the first fully connected layer of the target neural network model is determined by the first fully connected layer in the one-dimensional neural network model and the second fully connected layer in the two-dimensional neural network model.
[0118] In one embodiment, the first parsing module 302 may further include: parsing the unique identifier to obtain the target parsing address as the parsing result; and determining the service node that matches the parsing result as the first service node.
[0119] In one embodiment, the second parsing module 303 may specifically include: parsing the target device identifier and the maintenance identifier to obtain target device information and maintenance information; associating the target device information and the maintenance information to obtain association information; determining matching information in the first service node that matches the association information; determining the correlation coefficient between the association information and the matching information; determining the similarity result between the association information and the matching information based on the correlation coefficient; and using the similarity result as feedback information.
[0120] In one embodiment, such as Figure 4 As shown, the above-mentioned equipment maintenance device may further include: a second judgment module 401 and a second maintenance module 402. The structure will be described below.
[0121] The second judgment module 401 is used to determine the second service node by sending a request to the blockchain to obtain the target maintenance data when it is determined that the target maintenance data does not exist in the first service node; and to determine the second service node based on the request.
[0122] The second maintenance module 402 is used to receive target maintenance data fed back by the second service node, connect the target maintenance data to the target device, and perform maintenance on the target device based on the target maintenance data.
[0123] In some embodiments, the second determination module 401 may further include: determining multiple service nodes according to the acquisition request; calculating a set of Euclidean distances between the multiple service nodes and the target device; performing comparison processing on each Euclidean distance in the set of Euclidean distances to obtain a comparison processing result; and determining the target service node corresponding to the minimum value in the comparison processing result as the second service node.
[0124] It should be noted that the units, devices, or modules described in the above embodiments can be implemented by computer chips or physical entities, or by products with certain functions. For ease of description, the above devices are described by dividing them into various modules according to their functions. Of course, in implementing this specification, the functions of each module can be implemented in one or more software and / or hardware, or the module that implements the same function can be implemented by a combination of multiple sub-modules or sub-units, etc. The device embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and there may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection between the devices or units shown or discussed can be through some interfaces, and the indirect coupling or communication connection between devices or units can be electrical, mechanical, or other forms.
[0125] Therefore, the equipment maintenance device provided in the embodiments of this specification can achieve the following technical effects: On the one hand, it can predict equipment faults in advance, compare the fault prediction results with a preset threshold, and when the fault is less than the preset threshold, it can promptly obtain maintenance data to repair the equipment, thereby improving equipment utilization and ensuring normal equipment operation. On the other hand, by parsing the unique identifier, the first service node can be quickly queried. By parsing the target device identifier and maintenance identifier, it can be determined whether maintenance data exists in the first service node, improving the efficiency of maintenance data acquisition. When maintenance data exists, it is determined whether the device has maintenance data reading permissions. If so, the maintenance data is promptly connected to the device for maintenance, improving maintenance efficiency.
[0126] This application also provides a computer device, including a processor and a memory for storing processor-executable instructions. In a specific implementation, the processor can perform the following steps according to the instructions: acquiring target vibration data of a target device; inputting the target vibration data into a pre-built fault prediction model to obtain a fault prediction result for the target device, wherein the pre-built fault prediction model is trained based on a first feature vector and a second feature vector, the first feature vector and the second feature vector being determined by vibration sample data and fault sample data, respectively; determining whether the fault prediction result is less than a preset threshold; if it is determined to be less than the preset threshold, acquiring a unique identifier; parsing the unique identifier to determine the fault prediction result based on the parsed data. The results determine the first service node; a repair search request carrying identification information is sent to the first service node, wherein the identification information includes a target device identifier and a repair identifier; feedback information is received from the first service node, wherein the feedback information is determined based on the parsing results of the target device identifier and the repair identifier; based on the feedback information, it is determined whether target repair data exists in the first service node; if target repair data exists, it is determined whether the target device has the permission to read the target repair data; if the target device has the permission to read the target repair data, the target repair data is connected to the target device to perform repair on the target device based on the target repair data.
[0127] To execute the above instructions more accurately, please refer to... Figure 5 This application also provides another specific computer device, wherein the computer device includes a network communication port 501, a processor 502 and a memory 503, and the above structures are connected by internal cables so that the various structures can perform specific data interaction.
[0128] Specifically, the network communication port 501 can be used to acquire target vibration data of the target device, input the target vibration data into a pre-built fault prediction model, and obtain the fault prediction result of the target device. The pre-built fault prediction model is trained based on a first feature vector and a second feature vector, which are determined by vibration sample data and fault sample data, respectively.
[0129] The processor 502 can specifically be used to determine whether the fault prediction result is less than a preset threshold. When it is determined to be less than the preset threshold, it obtains a unique identifier, parses the unique identifier, and determines a first service node based on the parsing result. It then sends a maintenance search request carrying identification information to the first service node, wherein the identification information includes a target device identifier and a maintenance identifier. It receives feedback information from the first service node, wherein the feedback information is determined based on the parsing result of the target device identifier and the maintenance identifier. Based on the feedback information, it determines whether target maintenance data exists in the first service node. When it is determined that target maintenance data exists, it determines whether the target device has the permission to read the target maintenance data. When it is determined that the target device has the permission to read the target maintenance data, it connects the target maintenance data to the target device to perform maintenance on the target device based on the target maintenance data.
[0130] The memory 503 can be used to store the corresponding instruction program.
[0131] In this embodiment, the network communication port 501 can be a virtual port bound to different communication protocols, thereby enabling the sending or receiving of different data. For example, the network communication port can be a port responsible for web data communication, a port responsible for FTP data communication, or a port responsible for email data communication. Furthermore, the network communication port can also be a physical communication interface or communication chip. For example, it can be a wireless mobile network communication chip, such as GSM or CDMA; it can also be a Wi-Fi chip; or it can be a Bluetooth chip.
[0132] In this embodiment, the processor 502 can be implemented in any suitable manner. For example, the processor can take the form of a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro)processor, logic gates, switches, application-specific integrated circuits (ASICs), programmable logic controllers, and embedded microcontrollers, etc. This specification is not limiting.
[0133] In this embodiment, the memory 503 may include multiple layers. In a digital system, anything that can store binary data can be a memory. In an integrated circuit, a circuit with storage function but no physical form is also called a memory, such as RAM, FIFO, etc. In a system, a storage device with a physical form is also called a memory, such as a memory stick, TF card, etc.
[0134] This application also provides a computer storage medium based on the above-described equipment maintenance method. The computer storage medium stores computer program instructions, which, when executed, perform the following: acquiring target vibration data of the target equipment; inputting the target vibration data into a pre-built fault prediction model to obtain a fault prediction result for the target equipment; wherein the pre-built fault prediction model is trained based on a first feature vector and a second feature vector, the first feature vector and the second feature vector being determined by vibration sample data and fault sample data, respectively; determining whether the fault prediction result is less than a preset threshold; if it is determined to be less than the preset threshold, acquiring a unique identifier; parsing the unique identifier to determine whether the fault prediction result is less than a preset threshold. The parsing result determines the first service node; a repair search request carrying identification information is sent to the first service node, wherein the identification information includes a target device identifier and a repair identifier; feedback information is received from the first service node, wherein the feedback information is determined based on the parsing result of the target device identifier and the repair identifier; based on the feedback information, it is determined whether target repair data exists in the first service node; if target repair data exists, it is determined whether the target device has read permission for the target repair data; if the target device has read permission for the target repair data, the target repair data is connected to the target device to perform repair on the target device based on the target repair data.
[0135] In this embodiment, the storage medium includes, but is not limited to, Random Access Memory (RAM), Read-Only Memory (ROM), Cache, Hard Disk Drive (HDD), or Memory Card. The memory can be used to store computer program instructions. The network communication unit can be an interface configured according to standards specified in the communication protocol for network connection communication.
[0136] In this embodiment, the specific functions and effects implemented by the program instructions stored in the computer storage medium can be explained in comparison with other implementation methods, and will not be repeated here.
[0137] While this specification provides the steps of operation for the methods described in the embodiments or flowcharts, more or fewer steps may be included based on conventional or non-inventive means. The order of steps listed in the embodiments is merely one possible order of execution among many steps and does not represent the only possible order. In actual device or client product execution, the methods shown in the embodiments or drawings may be executed sequentially or in parallel (e.g., in a parallel processor or multi-threaded processing environment, or even a distributed data processing environment). The terms "comprising," "including," or any other variations thereof are intended to cover a non-exclusive inclusion, such that a process, method, product, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, product, or apparatus. Without further limitations, the presence of other identical or equivalent elements in a process, method, product, or apparatus that includes said elements is not excluded. The terms "first," "second," etc., are used to denote names and do not indicate any particular order.
[0138] Those skilled in the art will also know that, besides implementing the controller using purely computer-readable program code, the same functions can be achieved by logically programming the method steps, making the controller function as logic gates, switches, application-specific integrated circuits (ASICs), programmable logic controllers (PLCs), and embedded microcontrollers. Therefore, such a controller can be considered a hardware component, and the devices within it used to implement various functions can also be considered structures within that hardware component. Alternatively, the devices used to implement various functions can be considered as both software modules implementing the method and structures within a hardware component.
[0139] This specification can be described in the general context of computer-executable instructions that are executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, classes, etc., that perform a specific task or implement a specific abstract data type. This specification can also be practiced in distributed computing environments, where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.
[0140] As can be seen from the above description of the embodiments, those skilled in the art can clearly understand that this specification can be implemented by means of software plus necessary general-purpose hardware platforms. Based on this understanding, the technical solutions of this specification can essentially be embodied in the form of a software product. This computer software product can be stored in a storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, mobile terminal, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments of this specification.
[0141] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to interchangeably. Each embodiment focuses on its differences from other embodiments. This specification can be used in numerous general-purpose or special-purpose computer system environments or configurations. Examples include: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable electronic devices, network PCs, minicomputers, mainframe computers, and distributed computing environments including any of the above systems or devices, etc.
[0142] Although this specification has been described by way of examples, those skilled in the art will recognize that many variations and modifications are possible without departing from the spirit of this specification, and it is intended that the appended claims cover such variations and modifications without departing from the spirit of this specification.
Claims
1. A method for equipment maintenance, characterized in that, include: The target vibration data of the target device is acquired, and the target vibration data is input into a pre-built fault prediction model to obtain the fault prediction result of the target device. The pre-built fault prediction model is trained based on a first feature vector and a second feature vector, and the first feature vector and the second feature vector are determined by vibration sample data and fault sample data, respectively. Determine whether the fault prediction result is less than a preset threshold. If it is determined to be less than the preset threshold, obtain a unique identifier and parse the unique identifier to determine the first service node based on the parsing result. A maintenance search request carrying identification information is sent to the first service node, wherein the identification information includes the target device identifier and the maintenance identifier; Receive feedback information from the first service node, wherein the feedback information is determined based on the parsing results of the target device identifier and the maintenance identifier; Based on the feedback information, determine whether the target maintenance data exists in the first service node; When it is determined that target maintenance data exists, it is determined whether the target device has the permission to read the target maintenance data; When it is determined that the target device has the permission to read the target maintenance data, the target maintenance data is connected to the target device so as to perform maintenance on the target device based on the target maintenance data; The feedback information is determined based on the parsing results of the target device identifier and the maintenance identifier, and includes: The target device identifier and the maintenance identifier are parsed to obtain target device information and maintenance information; The target device information and the maintenance information are associated to obtain associated information; Determine the matching information in the first service node that matches the associated information; Determine the correlation coefficient between the association information and the matching information; Based on the correlation coefficient, the similarity result between the associated information and the matching information is determined; The similarity results are used as feedback information; The method further includes: Obtain sharing permissions for the target device, and based on the sharing permissions, share the target maintenance data stored in the target device to devices that are the same as or similar to the target device, so that when the target device and / or similar devices experience a target fault, the same and / or similar devices can be repaired based on the target maintenance data, thereby improving maintenance efficiency.
2. The method according to claim 1, characterized in that, The process of parsing the unique identifier to determine the first service node based on the parsing result includes: The unique identifier is parsed to obtain the target parsing address, which is used as the parsing result. The service node that matches the parsing result is identified as the first service node.
3. The method according to claim 1, characterized in that, The pre-built fault prediction model is obtained by training based on a first feature vector and a second feature vector, wherein the first feature vector and the second feature vector are determined by vibration sample data and fault sample data, respectively, including: Acquire vibration sample data and fault sample data; Based on the vibration sample data, determine the time-frequency image corresponding to the vibration sample data; The fault sample data is input into a one-dimensional neural network model to obtain the first feature vector; The time-frequency image is input into a two-dimensional neural network model to obtain a second feature vector; The target neural network model is trained based on the first feature vector and the second feature vector to obtain a fault prediction model; wherein, the first fully connected layer of the target neural network model is determined by the first fully connected layer in the one-dimensional neural network model and the second fully connected layer in the two-dimensional neural network model.
4. The method according to claim 1, characterized in that, The step of determining whether target maintenance data exists in the first service node based on the feedback information also includes: When it is determined that the target maintenance data does not exist in the first service node, the first service node sends a request to the blockchain to retrieve the target maintenance data; Based on the acquisition request, the second service node is determined; The system receives target maintenance data fed back from the second service node and connects the target maintenance data to the target device to perform maintenance on the target device based on the target maintenance data.
5. The method according to claim 4, characterized in that, The step of determining the second service node based on the acquisition request includes: Based on the acquisition request, multiple service nodes are identified; Calculate the set of Euclidean distances between multiple service nodes and the target device; The Euclidean distances in the Euclidean distance set are compared to obtain the comparison results. The target service node corresponding to the minimum value in the comparison processing results is determined as the second service node.
6. An equipment maintenance device, characterized in that, include: The fault prediction module is used to acquire target vibration data of the target device, input the target vibration data into a pre-built fault prediction model, and obtain the fault prediction result of the target device. The pre-built fault prediction model is trained based on a first feature vector and a second feature vector, and the first feature vector and the second feature vector are determined by vibration sample data and fault sample data, respectively. The first parsing module is used to determine whether the fault prediction result is less than a preset threshold. When it is determined that the result is less than the preset threshold, a unique identifier is obtained and the unique identifier is parsed to determine the first service node based on the parsing result. The second parsing module is used to send a maintenance search request carrying identification information to the first service node, wherein the identification information includes a target device identifier and a maintenance identifier; and to receive feedback information from the first service node, wherein the feedback information is determined based on the parsing results of the target device identifier and the maintenance identifier. The first judgment module is used to determine whether the target maintenance data exists in the first service node based on the feedback information. The first maintenance module is used to determine whether the target device has the permission to read the target maintenance data when it is determined that target maintenance data exists; and when it is determined that the target device has the permission to read the target maintenance data, connect the target maintenance data to the target device to perform maintenance on the target device based on the target maintenance data. The feedback information is determined based on the parsing results of the target device identifier and the maintenance identifier, and includes: The target device identifier and the maintenance identifier are parsed to obtain target device information and maintenance information; The target device information and the maintenance information are associated to obtain associated information; Determine the matching information in the first service node that matches the associated information; Determine the correlation coefficient between the association information and the matching information; Based on the correlation coefficient, the similarity result between the associated information and the matching information is determined; The similarity results are used as feedback information; The device further includes: Obtain sharing permissions for the target device, and based on the sharing permissions, share the target maintenance data stored in the target device to devices that are the same as or similar to the target device, so that when the target device and / or similar devices experience a target fault, the same and / or similar devices can be repaired based on the target maintenance data, thereby improving maintenance efficiency.
7. The apparatus according to claim 6, characterized in that, Also includes: The second judgment module is used to send a request to the blockchain to obtain the target maintenance data when it is determined that the target maintenance data does not exist in the first service node. Based on the acquisition request, the second service node is determined; The second maintenance module is used to receive target maintenance data fed back by the second service node, connect the target maintenance data to the target device, and perform maintenance on the target device based on the target maintenance data.
8. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method of any one of claims 1 to 5.
9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the method of any one of claims 1 to 5.