Antibacterial laundry device and method thereof

Abstract

An antibacterial laundry device and method are disclosed. The device uses sensors to sense the quantity, material, and degree of soiling of clothing to generate a sensing result. This sensing result is then input into a pre-trained machine learning model to output a set of optimized antibacterial parameters, including a target temperature, a target ozone concentration, and a target irradiation time. Based on these optimized antibacterial parameters, a heater, an ozone generator, and an ultraviolet sterilizer are driven to coordinate and regulate ozone washing, dehydration, and ultraviolet sterilization treatments, thereby achieving the technical effects of high-efficiency antibacterial treatment, clothing protection, and energy saving.

Claims

1. An antibacterial laundry apparatus, comprising: a washing tub for containing clothing and washing water; a sensing module including multiple sensors for sensing the quantity of clothing, the material of the clothing, and the degree of soiling in the washing tub to generate a sensing result; a heater coupled to the washing tub for heating the washing water; an ozone generator coupled to the washing tub for generating ozone and injecting it into the washing water; an ultraviolet sterilizer for generating ultraviolet light to irradiate the clothing in the washing tub; a non-transitory computer-readable storage medium for storing multiple instructions and a machine learning model, the machine learning model being pre-trained based on a training dataset including multiple clothing features and their corresponding set of optimized antibacterial parameters; and a hardware processor electrically connected to the sensing module, the heater, the ozone generator, the ultraviolet sterilizer, and the non-transitory computer-readable storage medium, and executing the multiple instructions to be configured as follows: The sensing results are input into the machine learning model, causing the machine learning model to output the optimized antibacterial parameters corresponding to the sensing results, wherein... The optimized antibacterial parameters include a target temperature, a target ozone concentration, and a target irradiation time. The system drives the heater to adjust the temperature of the wash water to the target temperature and drives the ozone generator to produce ozone at the target ozone concentration and inject it into the wash water. The system controls the washing tub to execute a washing program to wash the clothes. After the washing program is completed, the system controls the washing tub to execute a spin-drying program to dehydrate the clothes and drives the ultraviolet sterilizer to generate ultraviolet light to irradiate and sterilize the clothes until the target irradiation time is met.

2. The antibacterial laundry appliance of claim 1, wherein the plurality of sensors includes a weight sensor, a material identification sensor and an optical sensor, the weight sensor being used to sense the quantity of the garments, the material identification sensor being used to sense the material of the garments, the optical sensor being used to sense the degree of staining, and allowing continuous recording of each sensed data for analysis and generation of a maintenance recommendation report including the probability of failure.

3. The antibacterial laundry device as claimed in claim 1, wherein the machine learning model is a deep neural network model, the training dataset further includes antibacterial effect data corresponding to different clothing materials, and the hardware processor is configured to dynamically adjust the target temperature, the target ozone concentration, and the target irradiation time based on the antibacterial effect data.

4. The antibacterial laundry device of claim 1, wherein the sensing module further includes a turbidity sensor for continuously sensing turbidity data of the washing water during the washing process of the clothes, and the hardware processor dynamically adjusts the target ozone concentration according to the change of the turbidity data.

5. The antibacterial laundry device of claim 4, wherein the hardware processor is further configured to: before driving the ozone generator, when the turbidity sensor senses that the turbidity data does not meet a preset standard, activate a water quality processor installed in the antibacterial laundry device to pre-treat the washing water until the turbidity data meets the preset standard, and then drive the ozone generator to generate ozone.

6. An antibacterial laundry method, comprising the following steps: Initially, clothes and washing water are placed in a washing tub. Multiple sensors are used to sense the quantity, material, and degree of soiling of the clothes in the tub to generate a sensing result. The sensing result is input into a machine learning model, which outputs a set of optimized antibacterial parameters corresponding to the sensing result. These optimized antibacterial parameters include a target temperature, a target ozone concentration, and a target irradiation time. The machine learning model is pre-trained using a training dataset containing multiple clothing features and their corresponding optimized antibacterial parameters. Based on these optimized antibacterial parameters, a heater is driven to adjust the temperature of the washing water to the target temperature, and an ozone generator is driven to produce ozone at the target concentration and inject it into the washing water. The washing tub is started to execute a washing program to wash the clothes. After the washing program is completed, the washing tub is controlled to execute a spin-drying program to dehydrate the clothes, and an ultraviolet sterilizer is driven to generate ultraviolet light to irradiate and sterilize the clothes until the target irradiation time is met.

7. The antibacterial laundry method of claim 6, wherein the plurality of sensors includes a weight sensor, a material identification sensor and an optical sensor, the weight sensor being used to sense the quantity of the garments, the material identification sensor being used to sense the material of the garments, the optical sensor being used to sense the degree of staining, and allowing continuous recording of each sensed data for analysis, and generating a maintenance recommendation report including the probability of failure.

8. The antibacterial laundry method of claim 6, wherein the machine learning model is a deep neural network model, the training dataset further includes antibacterial effect data corresponding to different clothing materials, and the target temperature, the target ozone concentration and the target irradiation time are dynamically adjusted according to the antibacterial effect data.

9. The antibacterial laundry method of claim 6, wherein the plurality of sensors further includes a turbidity sensor for continuously sensing turbidity data of the wash water during the washing of the clothes, and dynamically adjusting the target ozone concentration based on changes in the turbidity data.

10. The antibacterial laundry method of claim 9, wherein the method further includes, before driving the ozone generator, when the turbidity sensor detects that the turbidity data does not meet a preset standard, starting a water quality processor to pre-treat the wash water until the turbidity data meets the preset standard, and then driving the ozone generator to generate ozone.

Images