Abnormality detection device, abnormality detection method, abnormality detection program, and recording medium
An anomaly detection and object detection technology, which is applied in electrical testing/monitoring, testing/monitoring control systems, instruments, etc., can solve problems such as cost-effectiveness of databases with large storage capacity, setting databases, etc.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
no. 1 approach
[0062] figure 1 It is a figure of the example of the structure of the abnormality detection apparatus 1a. The abnormality detection device 1a is an information processing device such as a personal computer, a workstation, or the like. The abnormality detection device 1a may be, for example, an information processing unit included in a PLC (Programmable Logic Controller).
[0063] The abnormality detection device 1a acquires data (hereinafter referred to as "device data") related to a device to be detected, and analyzes the acquired device data. Device data need not be accumulated in a database with a large storage capacity. The detection target device is not limited to a specific device, for example, a motor or a pump installed in a production facility. The device data is data of physical quantities, such as actual data of vibration, temperature, current, torque, pressure, flow rate, and the like. The device data may be an indication value provided to the device, for examp...
no. 2 approach
[0119] The second embodiment differs from the first embodiment in that the abnormality detection device includes a post-processing unit.
[0120] In the second embodiment, differences from the first embodiment will be described.
[0121] Figure 4 It is a figure which shows the example of the structure of the abnormality detection apparatus 1b. The abnormality detection device 1 b includes an acquisition unit 2 , a clipping unit 3 , a feature extraction unit 4 , a model processing unit 5 b , an output unit 6 , and a post-processing unit 7 . The model processing unit 5b includes a learning unit 50, a storage unit 51, and a divergence calculation unit 52b.
[0122] The post-processing unit 7 acquires the calculated divergence from the divergence calculation unit 52b. The post-processing unit 7 calculates the divergence every certain period. For example, the post-processing unit 7 may calculate an average value of divergence (simple moving average) for a predetermined number ...
no. 3 approach
[0127] The third embodiment differs from the first embodiment in that the abnormality detection device includes a plurality of model processing units. In the third embodiment, differences from the first embodiment will be described.
[0128] Image 6 It is a figure which shows the example of the structure of the abnormality detection apparatus 1c. The abnormality detection device 1 c includes an acquisition unit 2 , a cutout unit 3 , a feature extraction unit 4 , M (M is an integer greater than or equal to 2) model processing units 5 c , an output unit 6 , and a synthesis unit 8 . The model processing unit 5c of the abnormality detection device 1c is multiplied. The model processing unit 5 c includes a learning unit 50 , a storage unit 51 , a divergence calculation unit 52 c , and a selection unit 53 .
[0129] When the learning control signal indicates ON, the selection unit 53 acquires the extracted feature vector from the feature extraction unit 4 . The selection unit 5...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More