| CPC B08B 9/04 (2013.01) [B08B 9/00 (2013.01); B08B 9/02 (2013.01); B08B 9/027 (2013.01); B08B 9/032 (2013.01)] | 7 Claims |
|
1. A pipeline overturning lining inner wall cleaner, comprising a cleaner body (1), wherein one end of the cleaner body (1) is fixedly connected with a fixed block (2), one end of an outer side of the cleaner body (1) is provided with a first spring (3), one end of the first spring (3) is fixedly connected with a sleeve (4), the outer side of the cleaner body (1) is fixedly connected with a rotating base (5), one side of the rotating base (5) is provided with a first connecting rod (6), one side of the first connecting rod (6) is provided with a second connecting rod (7), the second connecting rod (7) is connected with an outer side of the sleeve (4), one end of the first connecting rod (6) is provided with a bracket (9), two ends of the bracket (9) are symmetrically and rotatably connected with rollers (10), one end of each roller (10) is fixedly connected to an output end of a first motor (12), the other end of the cleaner body (1) is fixedly connected with a box body (13), a second motor (14) is fixedly connected inside the box body (13), an output end of the second motor (14) is fixedly connected with a rotating table (15), a sliding groove (16) is disposed inside the rotating table (15), one side of an interior of the sliding groove (16) is fixedly connected with a second spring (17), one end of the second spring (17) is fixedly connected with a sliding block (18), one side of the sliding block (18) is fixedly connected with a supporting block (19), one side of the supporting block (19) is fixedly connected with a cleaning brush (20), a water pump (23) is fixedly connected inside the cleaner body (1), a shunt pipe (24) is fixedly connected inside the box body (13), one end of the shunt pipe (24) is fixedly connected with a drain pipe (25), and one end of the drain pipe (25) is fixedly connected with an atomizing nozzle (26); the cleaner body is a hollow pipeline, and an inner wall cleaning judgment device for detecting cleanliness of an inner wall is further fixedly disposed inside the cleaner body; the inner wall cleaning judgment device comprises a battery, a vibration sensor, a chip, and a communicator; the battery, the vibration sensor, the chip, and the communicator are all fixedly disposed on the inner wall of the cleaner body; the vibration sensor is electrically connected to the chip, the chip is electrically connected to the communicator, the battery is configured to supply power to the vibration sensor, the chip, and the communicator, the vibration sensor is configured to collect vibration of the inner wall of the cleaner body and transmit a vibration signal to the chip, and an inner wall cleaning judgment module that is configured to judge the cleanliness of the inner wall based on the vibration signal and transmit a cleanliness signal to an external receiving terminal through the communicator is disposed inside the chip; and the inner wall cleaning judgment module is configured to execute the following steps:
acquiring the vibration signal of the inner wall of the cleaner body;
performing preprocessing including denoising, filtering, and enhancement on the vibration signal to obtain preprocessing signals;
deleting signals generated by vibration of the rotating table itself from the preprocessing signals by utilizing a frequency discrimination approach to obtain a first signal;
performing feature extraction on the first signal to acquire a first signal feature;
inputting the first signal feature into a pretrained vibration cleanliness model to output cleanliness of an inner wall of a pipeline; wherein
steps of establishing and training the vibration cleanliness model specifically comprise three steps: establishing a training sample, establishing a prototype model, and training the prototype model;
the step of establishing a training sample specifically comprises:
acquiring a plurality of pipelines, and acquiring a vertically-shot image of an inner wall of each pipeline as a first image;
fixing different numbers of protrusions on an inner side of each pipeline, acquiring a vertically-shot image of the inner wall of each pipeline as a second image, determining a similarity between the second image and the first image, and using the similarity as cleanliness;
placing the pipeline overturning lining inner wall cleaner into the pipelines for cleaning, and recording a first signal generated at this time; and
taking the cleanliness obtained from a plurality of steel pipes and the first signal as the training sample;
the step of establishing a prototype model specifically comprises: establishing the prototype model by using a convolutional neural network; and
the step of training the prototype model specifically comprises: training the prototype model by using the training sample to obtain the vibration cleanliness model.
|