Inspection method and system based on big data

Abstract

The invention discloses an inspection method and system based on big data, and belongs to the technical field of industrial equipment inspection, and the method comprises the steps: obtaining a historical operation data set of hardware equipment, preprocessing the historical operation data, generating a training data set, training the training data set, building an equipment detection model, and installing the equipment detection model at an inspection terminal. A monitoring sensor is installed on hardware equipment, the monitoring sensor monitors the hardware equipment in real time and collects operation data of the hardware equipment in the operation process, an integrated repeater receives the operation data monitored and collected by the monitoring sensor, the data are sorted, integrated and calculated, and an operation state fluctuation diagram of each piece of hardware equipment is generated; an inspector carries the inspection terminal to inspect, uses the equipment detection model to detect the running state fluctuation diagram and judges the state of the hardware equipment, so that the inspection accuracy can be improved, only the integrated repeater needs to be inspected, and the labor cost and the false touch rate are reduced.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of industrial equipment inspection, and particularly relates to an inspection method and system based on big data. BACKGROUND

[0002] In an industrial production process, a large amount of data information is generated by various hardware devices every day. Workers need to inspect the equipment in the factory at fixed intervals to ensure the safety of various devices. The inspection personnel hold an inspection terminal and obtain inspection information at fixed inspection points in turn.

[0003] Since the hardware devices are generally more and the distances between them are farther, manual detection of the hardware devices one by one has poor operability, consumes a large amount of time, and the inspection quality is difficult to be stably ensured, and errors, loss and changes of the inspection records are prone to occur, resulting in poor real accuracy of the inspection records. Meanwhile, the existing inspection method has strong dependence on people, and only the special personnel who master the inspection standards and are responsible can perform safe and accurate inspection, which increases the human resource cost and error rate of the inspection. SUMMARY

[0004] To solve the above problems and technical defects, the application adopts the following technical solution: an inspection method based on big data, comprising the following steps:

[0005] Step 1: obtaining a historical running data set of hardware devices, preprocessing the historical running data to generate a training data set, training the training data set, establishing a device detection model, and installing the device detection model on an inspection terminal.

[0006] Step 2: installing a monitoring sensor on the hardware device, the monitoring sensor performing real-time monitoring on the hardware device and collecting running data of the hardware device in the running process.

[0007] Step 3: integrating a repeater to receive the running data collected by the monitoring sensor, integrating and calculating the data to generate a running state fluctuation graph of each hardware device.

[0008] Step 4: an inspection personnel carries out inspection by carrying an inspection terminal, the inspection terminal establishes a communication connection with the integrated repeater, and the device detection model is used to detect the running state fluctuation graph and judge the state of the hardware device.

[0009] Preferably, the preprocessing is to remove abnormal defect data in the historical running data set, to perform digital normalization processing on the remaining data to generate standardized data, to perform data reconstruction on the standardized data by using data augmentation, and to use the data set after the data reconstruction as the training data set.

[0010] Preferably, the establishment process of the device detection model comprises:

[0011] According to the device type, the training data set is classified, and data processing is performed on each type of training data set to generate a training subset;

[0012] The lightweight feature extractor extracts features from the training subset to obtain the running features of each type of device;

[0013] According to the running state, the running features are classified to obtain the state features of each type of device;

[0014] The state features are trained and calculated to obtain a state judgment model, and the state judgment model of each type of device in each running state is cross-scale feature fusion to generate a device detection model.

[0015] Further, the generation of the running state fluctuation graph of each hardware device comprises:

[0016] According to the time sequence, the running data is divided into data queues of fixed time length;

[0017] The convolutional neural network is used to extract the fluctuation features and time features in the data queue;

[0018] Based on the fluctuation features, a running fluctuation matrix is generated, and the running fluctuation matrix is adjusted according to the data dimension;

[0019] Based on the time features, the running fluctuation matrix is converted to generate a running state fluctuation graph.

[0020] Further, the device detection model detects the running state fluctuation graph, comprising:

[0021] Feature extraction is performed on the running state fluctuation graph to obtain the running features of the target device;

[0022] According to the model of the target device, the running features of the target device are matched with the running features of the corresponding device to obtain the corresponding state judgment model;

[0023] The state judgment model is used to extract features from the running state fluctuation graph to obtain state fluctuation features;

[0024] Based on the state fluctuation features and the running features of the corresponding device, the similarity is matched to obtain the current running state of the target device.

[0025] Further, the historical running data set further includes a fault case, the fault case includes fault running data, fault reason and fault repair measure, when the device detection model detects that the current running state of the target device is a fault running, the fault reason and the fault repair measure are output, so that the inspection personnel can repair the device according to the fault repair measure.

[0026] Further, the inspection terminal has a positioning map model established therein, comprising:

[0027] Download and install an inspection map model of the inspection site, number the monitoring sensors and integrated repeaters;

[0028] When the monitoring sensors and integrated repeaters are installed, mark the installation site in the inspection map model, and bind the number with the mark;

[0029] When the monitoring sensors upload the running data to the integrated repeaters, the number of the monitoring sensors will be sent;

[0030] When the device detection model detects that the current running state of the target device is a fault running, the inspection map model will highlight the corresponding mark.

[0031] A kind of inspection system based on big data, comprising:

[0032] Monitoring acquisition module, installed on hardware device, for real-time monitoring of hardware device, collecting running data of hardware device in running process;

[0033] Integrated relay module, for receiving the running data monitored and collected by monitoring acquisition module, integrating and calculating data, generating the running state fluctuation chart of each hardware device;

[0034] Inspection terminal, for installing device detection model, establishing communication connection with integrated relay module, using device detection model to detect running state fluctuation chart, and judging the state of hardware device.

[0035] An electronic device, comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor executes the program to realize the content of the above-described inspection method based on big data.

[0036] A computer-readable storage medium having a computer program stored thereon, wherein the computer program is executable by a processor to realize the content of the above-described inspection method based on big data.

[0037] Compared with the prior art, the application has the following advantages:

[0038] The application establishes a device detection model, installs the device detection model in the inspection terminal, uses the monitoring sensors to monitor the hardware devices in real time, uses the integrated repeaters to integrate and calculate data, generates the running state fluctuation chart of each hardware device, and uses the device detection model to detect the running state fluctuation chart and judge the state of the hardware device, thereby improving the accuracy of inspection, reducing the labor cost and the rate of false touch by only inspecting the integrated repeaters. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In the attached figure:

[0040] Figure 1 A schematic diagram of the method steps of an embodiment of the present application;

[0041] Figure 2 A schematic diagram of the system structure of an embodiment of the present application;

[0042] Figure 3 This is a schematic diagram of the device structure of an embodiment of the present application. DETAILED DESCRIPTION

[0043] In order to make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below in combination with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Generally, the components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various different configurations.

[0044] Example 1

[0045] like Figure 1 As shown, a patrol inspection method based on big data includes the following steps:

[0046] Obtain historical operation data sets of hardware devices, pre-process the historical operation data, generate training data sets, train the training data sets, establish equipment detection models, and install the equipment detection models on inspection terminals;

[0047] Preprocessing is to remove abnormal defect data in the historical operation data set, digitally normalize the remaining data to generate standardized data, use data augmentation to reconstruct the standardized data, and use the reconstructed data set as the training data set.

[0048] The process of establishing a device detection model includes:

[0049] Classify the training data set according to device type, process each type of training data set, and generate training subsets;

[0050] The lightweight feature extractor extracts features from the training subset to obtain the operating characteristics of each type of device;

[0051] Classify the operating characteristics according to the operating status and obtain the status characteristics of each type of equipment;

[0052] The state features are trained and calculated to obtain the state judgment model. The state judgment model of each type of equipment and each operating state is fused across scale features to generate a device detection model.

[0053] A monitoring sensor is installed on the hardware device, which monitors the hardware device in real time and collects running data of the hardware device during operation;

[0054] The integrated repeater receives the running data collected by the monitoring sensor, organizes and integrates the data, and generates a running state fluctuation graph of each hardware device;

[0055] Generating a running state fluctuation graph of each hardware device includes:

[0056] According to the time sequence, the running data will be divided into data queues of fixed time length;

[0057] Convolutional neural network is used to extract fluctuation features and time features in the data queue;

[0058] Based on the fluctuation features, a running fluctuation matrix is generated, and the running fluctuation matrix is adjusted in weight according to the data dimension;

[0059] Based on the time features, the running fluctuation matrix is converted to generate a running state fluctuation graph.

[0060] The inspection personnel carry an inspection terminal for inspection, the inspection terminal establishes a communication connection with the integrated repeater, and uses a device detection model to detect the running state fluctuation graph and judge the state of the hardware device.

[0061] The device detection model detects the running state fluctuation graph, which includes:

[0062] Feature extraction is performed on the running state fluctuation graph to obtain the running features of the target device;

[0063] According to the model of the target device, the running features of the target device are matched with the running features of the corresponding device to obtain a corresponding state judgment model;

[0064] The state judgment model is used to extract features from the running state fluctuation graph to obtain state fluctuation features;

[0065] Based on the similarity matching between the state fluctuation features and the running features of the corresponding device, the current running state of the target device is obtained.

[0066] The historical running data set also includes fault cases, which include fault running data, fault reasons and fault repair measures. When the device detection model detects that the current running state of the target device is a fault running, it will output the fault reason and the fault repair measure, so that the inspection personnel can repair the device according to the fault repair measure.

[0067] A positioning map model is established in the inspection terminal, which includes:

[0068] Download and install the inspection map model of the inspection site, number the monitoring sensors and integrated repeaters;

[0069] When installing the monitoring sensors and integrated repeaters, mark the installation site in the inspection map model, and bind the number with the mark;

[0070] When the monitoring sensors upload the running data to the integrated repeaters, the number of the monitoring sensors will be sent;

[0071] When the device detection model detects that the current running state of the target device is a fault running state, the inspection map model will highlight the corresponding mark.

[0072] Embodiment 2

[0073] As shown in Figure 2 , a big data-based inspection system includes:

[0074] A monitoring and collecting module is installed on a hardware device, and is used to monitor the hardware device in real time, and collect the running data of the hardware device during the running process;

[0075] An integrated relay module is used to receive the running data collected by the monitoring and collecting module, to arrange, integrate and calculate the data, and to generate a running state fluctuation graph of each hardware device;

[0076] An inspection terminal is used to install a device detection model, to establish a communication connection with the integrated relay module, to detect the running state fluctuation graph using the device detection model, and to judge the state of the hardware device.

[0077] Embodiment 3

[0078] As shown in Figure 3 , from the hardware level, the present application provides an embodiment of an electronic device including all or part of the content of the BBB, which includes a service processor and a distributed memory, the service processor is connected to the memory, the distributed memory stores a service self-management program, and is configured to store machine-readable instructions, the service processor executes the service self-management program, and the instructions are executed by the processor to realize the BBB as described above.

[0079] From the hardware level, in order to effectively improve the flexibility, universality and collection efficiency of data collection, the present application provides an embodiment of an electronic device including all or part of the content of the BBB, which specifically includes the following content:

[0080] A processor, a memory, a communications interface, and a bus; wherein the processor, the memory, the communications interface complete the communication among each other through the bus; the communications interface is used to realize the information transmission between the core business system of the BBB, the user terminal, and the related database and other related devices; the logic controller can be a desktop computer, a tablet computer, a mobile terminal, and the like, and the embodiment is not limited thereto.

[0081] In the embodiment, the logic controller can be implemented according to the embodiment of the BBB in the embodiment, the content of which is incorporated herein, and the repeated parts will not be described again.

[0082] It can be understood that the user terminal can include a smart phone, a tablet electronic device, a network set-top box, a portable computer, a desktop computer, a personal digital assistant (PDA), a vehicle-mounted device, a smart wearable device, and the like, wherein the smart wearable device can include smart glasses, a smart watch, a smart bracelet, and the like.

[0083] In actual application, part of the BBB can be executed on the electronic device as described above, or all operations can be completed in the client device, and the specific selection can be made according to the processing capacity of the client device and the limitation of the user use scene, and the application is not limited thereto. If all operations are completed in the client device, the client device can further include a processor.

[0084] The above-mentioned client device can have a communication module (i.e., a communication unit) and can be communicatively connected with a remote server to realize the data transmission with the server, wherein the server can include a server on the task scheduling center side, and the server of an intermediate platform can also be included in other implementation scenarios, such as a server of a third-party server platform communicatively connected with the task scheduling center server, the server can include a single computer device, a server cluster composed of multiple servers, or a distributed server structure.

[0085] Embodiment 4

[0086] The embodiment of the application further provides a computer readable storage medium capable of realizing the BBB with the execution subject being the server or the client in the above-mentioned embodiments, and the computer readable storage medium has a computer program stored thereon, and the computer program is executed by the processor to realize the whole content of the BBB with the execution subject being the server or the client in the above-mentioned embodiments.

[0087] Embodiments of the present application can be provided as a method, apparatus, or computer program product, thus the present application can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects, and the present application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied thereon.

[0088] The embodiments of the present application are described with reference to the flowchart and / or block diagram of the method, apparatus (device), and computer program product according to the embodiments of the present application, it should be understood that each flow and / or block in the flowchart and / or block diagram and combination of flows and / or blocks in the flowchart and / or block diagram can be implemented by computer program instructions, and these computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing apparatus to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing apparatus generate a means for implementing the functions specified in the flowchart and / or block diagram. Figure 1 The flow and / or block Figure 1 The apparatus for implementing the functions specified in the flow and / or block.

[0089] These computer program instructions can also be stored in a computer-readable memory capable of directing the computer or other programmable data processing apparatus to work in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including instruction apparatus, which implements the functions specified in the flowchart and / or block diagram. Figure 1 The flow and / or block Figure 1 The functions specified in the flow and / or block.

[0090] These computer program instructions can also be loaded into a computer or other programmable data processing apparatus, so that a series of operation steps are performed on the computer or other programmable data processing apparatus to produce a computer-implemented process, so that the instructions executed on the computer or other programmable data processing apparatus provide a process for implementing the functions specified in the flowchart and / or block diagram. Figure 1 The flow and / or block Figure 1 The functions specified in the flow and / or block.

[0091] The above-described embodiments only express the preferred embodiments of the present application, the description is more specific and detailed, but it cannot be understood as limiting the scope of the patent of the present application. It should be pointed out that for ordinary skilled in the art, without departing from the concept of the present application, a number of modifications, improvements and substitutions can be made, which are within the scope of protection of the present application.

Claims

1. A patrol inspection method based on big data, characterized in that: The following steps are involved: Step 1: Obtain the historical operation data set of the hardware equipment, pre-process the historical operation data, generate a training data set, train the training data set, establish a device detection model, and install the device detection model on the inspection terminal; Step 2: Install monitoring sensors on the hardware devices to monitor the hardware devices in real time and collect operating data of the hardware devices during operation; Step 3: The integrated repeater receives the operating data collected by the monitoring sensor, organizes and integrates the data, and generates an operating status fluctuation graph for each hardware device; Step 4: The inspection personnel carry the inspection terminal to conduct inspections. The inspection terminal establishes a communication connection with the integrated repeater, uses the equipment detection model to detect the operation status fluctuation diagram, and determines the status of the hardware equipment.

2. The inspection method based on big data according to claim 1, characterized in that: The preprocessing is to remove abnormal defect data in the historical operation data set, perform digital normalization on the remaining data to generate standardized data, use data augmentation to reconstruct the standardized data, and use the reconstructed data set as the training data set.

3. The inspection method based on big data according to claim 1, characterized in that: The process of establishing the device detection model includes: Classify the training data set according to device type, process each type of training data set, and generate training subsets; The lightweight feature extractor extracts features from the training subset to obtain the operating characteristics of each type of device; Classify the operating characteristics according to the operating status and obtain the status characteristics of each type of equipment; The state features are trained and calculated to obtain the state judgment model. The state judgment model of each type of equipment and each operating state is fused across scale features to generate a device detection model.

4. The inspection method based on big data according to claim 3, characterized in that: Generating the operation status fluctuation graph of each hardware device includes: According to the time series, the running data will be divided into data teams of fixed time length; Use convolutional neural networks to extract fluctuation and time features from data sets; Generate an operating fluctuation matrix based on the fluctuation characteristics, and adjust the weight of the operating fluctuation matrix according to the data dimension; The operation fluctuation matrix is ​​transformed based on the time characteristics to generate an operation status fluctuation graph.

5. The inspection method based on big data according to claim 3, characterized in that: The device detection model detects the operation status fluctuation graph including: Extract features from the operating status fluctuation graph to obtain the operating characteristics of the target device; According to the model of the target device, the operating characteristics of the target device are matched with the operating characteristics of the corresponding device to obtain the corresponding state judgment model; Use the state judgment model to extract features from the running state fluctuation graph to obtain state fluctuation features; Based on the similarity matching between the state fluctuation characteristics and the operating characteristics of the corresponding device, the current operating status of the target device is obtained.

6. The inspection method based on big data according to claim 5, characterized in that: The historical operation data set also includes fault cases, which include fault operation data, fault causes and fault repair measures. When the equipment detection model detects that the current operating status of the target equipment is faulty operation, it will output the fault cause and fault repair measures, so that the inspection personnel can perform equipment repair according to the fault repair measures.

7. The inspection method based on big data according to claim 5, characterized in that: A positioning map model is established in the inspection terminal, including: Download and install the inspection map model of the inspection site, and number the monitoring sensors and integrated repeaters; When installing monitoring sensors and integrated repeaters, mark the installation locations in the inspection map model and bind the numbers to the marks; When the monitoring sensor uploads the operating data to the integrated repeater, it also sends its own number; When the device detection model detects that the current operating status of the target device is faulty, the inspection map model will highlight the corresponding mark.

8. A patrol inspection system based on big data, characterized in that: include: The monitoring and acquisition module is installed on the hardware device and is used to monitor the hardware device in real time and collect the operating data of the hardware device during operation; The integrated relay module is used to receive the operating data collected by the monitoring and acquisition module, organize and integrate the data, and generate an operating status fluctuation chart for each hardware device; The inspection terminal is used to install the equipment detection model, establish a communication connection with the integrated relay module, use the equipment detection model to detect the operation status fluctuation diagram, and judge the status of the hardware equipment.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the content of the inspection method based on big data described in claim 1 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the content of the inspection method based on big data described in claim 1 is realized.

Images