Intelligent water taking device of direct drinking water terminal

Abstract

The invention discloses an intelligent water taking device for a direct drinking water terminal, solves the problems of multi-type water taking of a pipeline direct drinking water terminal and intelligent sterilization of a pipe network, and belongs to the technical field of terminal water taking. A sampling pool, a quick heating unit, a refrigerating unit and a water taking unit are arranged on a water supply and return pipeline; the control unit controls the quick heating unit, the refrigerating unit and the water taking unit to work according to an instruction input by the man-machine interaction unit; the Fourier lamination illumination light source enters the sampling pool in a staggered mode, the optical sensor receives diffracted light generated at different moments in the sampling pool, and a low-spatial-resolution three-dimensional image at each moment is obtained; the control unit controls the sampling pool to sample water in the water supply and return pipeline, then controls the Fourier laminated illumination light source and the optical sensor to work, reconstructs a high-spatial-resolution image, judges whether sterilization is needed or not, feeds back a sterilization signal to the upper end control module, and controls the front central water supply and return device to integrally sterilize the water supply and return system. And water safety is guaranteed from the source.

Description

Technical Field

[0001] The invention relates to an intelligent water-taking device for a direct drinking water terminal, belonging to the technical field of terminal water-taking. Background Art

[0002] With the continuous development of social economy, people's pursuit of quality of life is getting higher and higher. The drinking water industry is in urgent need of transformation and upgrading. The construction of urban pipeline direct drinking water can provide more reliable and convenient drinking water for urban residents, increase the increase of people's livelihood and happiness, and effectively protect drinking water safety. However, due to the instability of the quality of pipeline direct drinking water, the problem of bacteria and microorganisms in drinking water equipment has always been the focus of people's attention.

[0003] The monitoring of domestic water mainly includes the detection of chemical elements in samples, such as COD, TOC, ammonia nitrogen, fluoride, chloride, nitrate, nitrite, sulfate, phosphate, oil, etc., the detection of chemical and physical properties of samples, such as pH value, water temperature, conductivity, etc., and the distribution of microbial communities in the samples. The risk of biological water toxicity caused by microorganisms is the greatest. Especially in drinking water, the toxicity of microbial water quality is far greater than the pollution of heavy metals, disinfection by-products, and organic matter. The distribution of microbial communities is becoming an increasingly important part of the indicator system. If chemical elements and microorganisms that are harmful to humans exceed certain standards, corresponding safety alarms will be issued. Traditional water quality monitoring mainly relies on laboratory testing after sampling, which is limited in time and cost. In terms of direct drinking water sterilization, regular sterilization or manual control of sterilization according to user needs is adopted, which is obviously not smart enough. Summary of the invention

[0004] In order to solve the problems of multi-type water extraction and intelligent sterilization of pipe networks at pipeline direct drinking water terminals, the present invention provides an intelligent water extraction device for direct drinking water terminals.

[0005] The present invention discloses an intelligent water-taking device for a direct drinking water terminal, comprising a sampling pool, a Fourier stacked illumination light source, an optical sensor, a rapid heating unit, a refrigeration unit, a water-taking unit, a human-computer interaction unit and a control unit;

[0006] The water supply and return pipelines are provided with a sampling pool, a sterilization unit, a quick heating unit, a refrigeration unit and a water intake unit;

[0007] A human-computer interaction unit, used to input hot water instructions, cold water instructions, warm water instructions, quantitative water extraction instructions, and on-demand water extraction instructions, and send the input instructions to the control unit;

[0008] The control unit, when receiving hot water and warm water instructions, controls the quick heating unit to work and heats the water to the set temperature; when receiving a cold water instruction, controls the refrigeration unit to work and cools the water to the cold water set temperature; when receiving a quantitative water extraction instruction, controls the water extraction unit to work and output a set amount of water; when receiving an on-demand water extraction instruction, the water extraction unit outputs water until the on-demand water extraction instruction ends;

[0009] The two-dimensional array light emitted by the Fourier stack illumination light source is incident on the sampling pool at staggered times, and the optical sensor is used to receive the diffracted light generated in the sampling pool at different times, obtain a low spatial resolution three-dimensional image at each time, and send it to the control unit;

[0010] The control unit is also used to control the sampling pool to sample the water in the supply and return water pipelines. After the sampling is completed, it controls the operation of the Fourier stack illumination light source and the optical sensor, and reconstructs the low spatial resolution three-dimensional images received at each moment to obtain a high spatial resolution image. According to the obtained high spatial resolution image, it determines whether sterilization is needed, and feeds back the sterilization signal to the upper control module, so that the upper control module controls the front central supply and return water device to perform overall disinfection on the entire supply and return water system.

[0011] Preferably, the device further comprises a standard liquid unit and a waste cleaning unit;

[0012] The sampling pool is provided with two water inlets and one water outlet, and both are provided with valves. The first water inlet of the sampling pool is connected to the water supply and return pipeline, and the second water inlet of the sampling pool is connected to the standard liquid unit;

[0013] The control unit is also used to control the closing of the valves of the two water inlets and the opening of the valve of the drain outlet. When the water in the sampling pool is emptied, the valve of the drain outlet is controlled to close, the valve of the second water inlet is opened, and the standard liquid in the standard liquid unit is controlled to be pumped into the sampling pool. At this time, the Fourier stack illumination light source and the optical sensor are controlled to work, and the reconstructed high spatial resolution image is compared with the standard image to determine whether it is necessary to discharge waste and clean the pipeline. If so, the waste discharge and cleaning unit is controlled to discharge waste and clean the water supply and return pipelines.

[0014] The standard image is an image obtained by sampling the standard liquid in the sampling pool after the sampling pool is drained and cleaned, using a Fourier stack illumination light source and an optical sensor.

[0015] Preferably, a detection model is stored in the control unit, and the detection model is a model implemented based on a convolutional neural network and trained through a training set, and the training set is a high spatial resolution image collected from a sampling pool containing drinking water in different states, and the different states include those that require sterilization and those that do not require sterilization.

[0016] Preferably, the detection model is implemented using a convolutional neural network based on dynamic convolution, including 5 Conv3*3 convolutional layers, 2 downsampling layers, 2 upsampling layers, 2 splicing layers, 2 snake convolutional layers and 1 classification layer;

[0017] The preprocessed high spatial resolution image is input as the input image to the first Conv3*3 convolution layer. The output of the first Conv3*3 convolution layer is activated by the Relu activation function and enters the first downsampling layer and the first snake convolution layer at the same time. The output of the first downsampling layer enters the second Conv3*3 convolution layer. The output of the second Conv3*3 convolution layer is activated by the Relu activation function and enters the second downsampling layer and the second snake convolution layer at the same time.

[0018] The output of downsampling layer No. 2 enters Conv3*3 convolution layer No. 3, the output of Conv3*3 convolution layer No. 3 enters upsampling layer No. 1 after being activated by Relu activation function, the output of upsampling layer No. 1 and the output of snake convolution layer No. 2 enter splicing layer No. 1 at the same time, the output of splicing layer No. 1 enters Conv3*3 convolution layer No. 4, the output of Conv3*3 convolution layer No. 4 enters upsampling layer No. 2 after being activated by Relu activation function, the output of upsampling layer No. 2 and the output of snake convolution layer No. 1 enter splicing layer No. 2 at the same time, the output of splicing layer No. 2 enters Conv3*3 convolution layer No. 5, the output of Conv3*3 convolution layer No. 5 enters classification layer after being activated by Relu activation function, and the output of classification layer is output after being activated by activation function sigmoid.

[0019] Preferably, the device also includes a sterilization unit that utilizes ultraviolet rays to perform terminal disinfection.

[0020] Preferably, the device further comprises a metering unit, which is used to measure the water flowing through the pipeline and send the metering unit to the control unit.

[0021] Preferably, the device further comprises a prepayment unit, and the control unit counts the water consumption according to the metering unit, and displays the water fee and payment method to remind the user to pay.

[0022] Preferably, the device further comprises a data transmission module, and the control unit is used to transmit the water usage information to other terminals via the data transmission unit.

[0023] The beneficial effect of the present invention is that the present invention integrates the light field and Fourier stacking technology and reconstructs a three-dimensional image of drinking water, and uses the image to monitor whether the drinking water in the supply and return pipes needs to be sterilized, thereby ensuring the water quality of the water. The water intake device of the present invention can realize automatic monitoring and sterilization control to ensure the water quality of drinking water. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 It is a schematic diagram of the principle of the intelligent water intake device for direct drinking water terminal of the present invention, 1-household valve, 2-metering module, 3-disinfection module, 4-rapid heating module, 5-refrigeration module, 6-water intake module, 7-waste discharge module, 8-human-machine exchange module, 9-data transmission module;

[0025] Figure 2 It is a schematic diagram of the principle of the detection model of the present invention. DETAILED DESCRIPTION

[0026] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0027] It should be noted that, in the absence of conflict, the embodiments of the present invention and the features in the embodiments may be combined with each other.

[0028] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments, but they are not intended to limit the present invention.

[0029] The direct drinking water terminal intelligent water extraction device of this embodiment includes a sampling pool, a Fourier stacked lighting source, an optical sensor, a sterilization unit, a quick heating unit, a refrigeration unit, a water extraction unit, a human-computer interaction unit and a control unit;

[0030] The water supply and return pipelines are provided with a sampling pool, a sterilization unit, a quick heating unit, a refrigeration unit and a water intake unit;

[0031] A human-computer interaction unit, used to input hot water instructions, cold water instructions, warm water instructions, quantitative water extraction instructions, and on-demand water extraction instructions, and send the input instructions to the control unit;

[0032] The control unit, when receiving hot water and warm water instructions, controls the quick heating unit to work and heats the water to the set temperature; when receiving a cold water instruction, controls the refrigeration unit to work and cools the water to the cold water set temperature; when receiving a quantitative water extraction instruction, controls the water extraction unit to work and output a set amount of water; when receiving an on-demand water extraction instruction, the water extraction unit outputs water until the on-demand water extraction instruction ends; this embodiment can measure the amount of drinking water, extract water on demand, extract water in a quantitative manner, and can extract water in multiple modes according to personal needs, hot water, warm water, ice water, ready to use, no need to wait for heating or cooling;

[0033] The two-dimensional array light emitted by the Fourier stack illumination light source of this embodiment is incident on the sampling pool at different times. The optical sensor is used to receive the diffracted light generated at different times in the sampling pool, obtain a low spatial resolution three-dimensional image at each time, and send it to the control unit; Fourier stack imaging means imaging by folding multiple diffraction images. In today's stack imaging, an image is obtained by irradiating different positions of the sample to be tested with the illumination probe, which is a layer. Then, many layers can be obtained by moving the sample to be tested to different positions. Superimposing the layers can lock the phase relationship at different positions of the sample, and then the phase information can be reconstructed through the phase recovery algorithm.

[0034] The control unit is also used to control the sampling pool to sample the water in the supply and return water pipelines. After the sampling is completed, the Fourier stack illumination light source and the optical sensor are controlled to work, and the low spatial resolution three-dimensional images received at each moment are reconstructed to obtain high spatial resolution images. Whether sterilization is needed is determined based on the obtained high spatial resolution images. The images can be analyzed to determine whether the bacterial content in the images exceeds the standard. The analysis results are fed back to the upper control module to control the front supply and return water device to disinfect the entire supply and return water system as a whole, thereby ensuring water safety from the source.

[0035] The Fourier stacking reconstruction method needs to use the intensity constraints and overlap rate constraints of the original image to reconstruct the object spectrum. The basic principle of Fourier stacking reconstruction is to iteratively update the original image to obtain a synthetic spectrum and a restored image. Convolutional neural networks can also be used for reconstruction.

[0036] Because the sampling pool and the water supply and return pipes are used for a long time, there will be scale, which affects the water quality and the collection of images in the sampling pool. It is also necessary to drain and clean the water supply and return pipes and the sampling pool. This embodiment also includes a standard liquid unit and a waste cleaning unit.

[0037] The sampling pool is provided with two water inlets and one drain outlet, and both are provided with valves. The first water inlet of the sampling pool is connected to the water supply and return pipeline, and the second water inlet of the sampling pool is connected to the standard liquid unit;

[0038] The process of the control unit performing waste discharge cleaning control includes two stages, one is the detection stage, and the other is the waste discharge cleaning stage;

[0039] Detection stage: the control unit controls the valves of the two water inlets to close and the valve of the drain to open to prevent contamination of the water supply and return pipes. When the water in the sampling pool is emptied, the valve of the drain is controlled to close, the valve of the second water inlet is opened, and the standard liquid in the standard liquid unit is controlled to be pumped into the sampling pool. At this time, the Fourier stack illumination light source and the optical sensor are controlled to work, and the reconstructed high spatial resolution image is compared with the standard image to determine whether it is necessary to discharge waste and clean the pipeline. If so, the waste cleaning unit is controlled to discharge waste and clean the water supply and return pipelines.

[0040] The standard image is an image obtained by using a Fourier stack illumination light source and an optical sensor after the sampling pool has been drained and cleaned and the standard liquid has been sampled. It is used to measure whether the sampling pool needs to be cleaned and drained.

[0041] Wastewater cleaning stage: The central water supply and return module can be used to perform pipeline cyclic chemical washing. After the set time, the pipeline will be cyclically washed to ensure the water supply quality. During the pipeline chemical washing, the prompt "the equipment is being washed and water cannot be taken" will be displayed. After the chemical washing, the pipeline can be intelligently emptied and flushed with clean water. After the pipeline is flushed, the outlet valve of the supply and return pipe will be opened to drain the waste water from the branch pipeline.

[0042] The control unit of this embodiment stores a detection model, which is a model implemented based on a convolutional neural network and trained through a training set, and the training set is a high spatial resolution image collected from a sampling pool containing drinking water in different states, and the different states include sterilization and no sterilization. The detection model provided in this embodiment is implemented using a convolutional neural network based on dynamic convolution, including 5 Conv3*3 convolutional layers, 2 downsampling layers, 2 upsampling layers, 2 splicing layers, 2 serpentine convolutional layers and 1 classification layer;

[0043] The preprocessed high spatial resolution image is input as the input image to the first Conv3*3 convolution layer. The output of the first Conv3*3 convolution layer is activated by the Relu activation function and enters the first downsampling layer and the first snake convolution layer at the same time. The output of the first downsampling layer enters the second Conv3*3 convolution layer. The output of the second Conv3*3 convolution layer is activated by the Relu activation function and enters the second downsampling layer and the second snake convolution layer at the same time.

[0044] The output of downsampling layer No. 2 enters Conv3*3 convolution layer No. 3, the output of Conv3*3 convolution layer No. 3 enters upsampling layer No. 1 after being activated by Relu activation function, the output of upsampling layer No. 1 and the output of snake convolution layer No. 2 enter splicing layer No. 1 at the same time, the output of splicing layer No. 1 enters Conv3*3 convolution layer No. 4, the output of Conv3*3 convolution layer No. 4 enters upsampling layer No. 2 after being activated by Relu activation function, the output of upsampling layer No. 2 and the output of snake convolution layer No. 1 enter splicing layer No. 2 at the same time, the output of splicing layer No. 2 enters Conv3*3 convolution layer No. 5, the output of Conv3*3 convolution layer No. 5 enters classification layer after being activated by Relu activation function, and the output of classification layer is output after being activated by activation function sigmoid.

[0045] Although the downsampling layer in the network of this embodiment can reduce the amount of calculation and increase the receptive field, it also abandons part of the image information. Then, when the upsampling layer is used to restore the image size, the image information details will be lost. This embodiment has downsampling layers and upsampling layers. These two structures will cause a large amount of detail information loss, resulting in poor segmentation effect of the convolutional neural network. Therefore, dynamic snake convolution is introduced to compensate for the lost details and improve the network receptive field.

[0046] The sterilization unit of this embodiment uses ultraviolet rays to sterilize the water intake end. The ultraviolet sterilizer is an important part of the device and uses a high-efficiency ultraviolet lamp. The ultraviolet sterilizer can emit ultraviolet rays of a specific wavelength and has a strong sterilization ability.

[0047] The device in this embodiment further includes a metering unit and a prepayment unit. The metering unit is used to measure the water flowing through the pipeline and send it to the control unit.

[0048] The control unit counts the water consumption according to the metering unit, and displays the water fee and payment method. It is also equipped with an electric household valve to remind users to pay when they are in arrears. If the payment is not made within the time limit, the system will automatically close the household valve to stop the water supply. After the user has paid the water fee, the system will automatically open the valve and the user can continue to use water.

[0049] The device of this embodiment further includes a data transmission module, and the control unit is used to collect and transmit water use information and operation data in real time to other terminals through the data transmission unit.

[0050] Although the present invention is described herein with reference to specific embodiments, it should be understood that these embodiments are merely examples of the principles and applications of the present invention. It should therefore be understood that many modifications may be made to the exemplary embodiments and that other arrangements may be devised without departing from the spirit and scope of the present invention as defined by the appended claims. It should be understood that the various dependent claims and features described herein may be combined in a manner different from that described in the original claims. It should also be understood that features described in conjunction with individual embodiments may be used in other described embodiments.

Claims

1. Direct drinking water terminal intelligent water extraction device, characterized in that: It includes a sampling pool, a Fourier stack illumination light source, an optical sensor, a quick heating unit, a refrigeration unit, a water intake unit, a human-computer interaction unit and a control unit; The water supply and return pipelines are provided with a sampling pool, a sterilization unit, a quick heating unit, a refrigeration unit and a water intake unit; A human-computer interaction unit, used to input hot water instructions, cold water instructions, warm water instructions, quantitative water extraction instructions, and on-demand water extraction instructions, and send the input instructions to the control unit; The control unit, when receiving hot water and warm water instructions, controls the quick heating unit to work and heats the water to the set temperature; when receiving a cold water instruction, controls the refrigeration unit to work and cools the water to the cold water set temperature; when receiving a quantitative water extraction instruction, controls the water extraction unit to work and output a set amount of water; when receiving an on-demand water extraction instruction, the water extraction unit outputs water until the on-demand water extraction instruction ends; The two-dimensional array light emitted by the Fourier stack illumination light source is incident on the sampling pool at staggered times, and the optical sensor is used to receive the diffracted light generated in the sampling pool at different times, obtain a low spatial resolution three-dimensional image at each time, and send it to the control unit; The control unit is also used to control the sampling pool to sample the water in the supply and return water pipelines. After the sampling is completed, it controls the operation of the Fourier stack illumination light source and the optical sensor, and reconstructs the low spatial resolution three-dimensional images received at each moment to obtain a high spatial resolution image. According to the obtained high spatial resolution image, it determines whether sterilization is needed, and feeds back the sterilization signal to the upper control module, so that the upper control module controls the front central supply and return water device to perform overall disinfection on the entire supply and return water system.

2. The intelligent water intake device for direct drinking water terminal according to claim 1 is characterized in that: The device also includes a standard liquid unit and a waste cleaning unit; The sampling pool is provided with two water inlets and one water outlet, and both are provided with valves. The first water inlet of the sampling pool is connected to the water supply and return pipeline, and the second water inlet of the sampling pool is connected to the standard liquid unit; The control unit is also used to control the closing of the valves of the two water inlets and the opening of the valve of the drain outlet. When the water in the sampling pool is emptied, the valve of the drain outlet is controlled to close, the valve of the second water inlet is opened, and the standard liquid in the standard liquid unit is controlled to be pumped into the sampling pool. At this time, the Fourier stack illumination light source and the optical sensor are controlled to work, and the reconstructed high spatial resolution image is compared with the standard image to determine whether it is necessary to discharge waste and clean the pipeline. If so, the waste discharge and cleaning unit is controlled to discharge waste and clean the water supply and return pipelines. The standard image is an image obtained by sampling the standard liquid in the sampling pool after the sampling pool is drained and cleaned, using a Fourier stack illumination light source and an optical sensor.

3. The intelligent water intake device for direct drinking water terminal according to claim 1 is characterized in that: The control unit stores a detection model, which is a model implemented based on a convolutional neural network and trained through a training set. The training set is a high spatial resolution image collected from a sampling pool containing drinking water in different states, wherein the different states include those requiring sterilization and those not requiring sterilization.

4. The intelligent water intake device for direct drinking water terminal according to claim 3 is characterized in that: The detection model is implemented using a convolutional neural network based on dynamic convolution, including 5 Conv3*3 convolutional layers, 2 downsampling layers, 2 upsampling layers, 2 splicing layers, 2 snake convolutional layers and 1 classification layer; The preprocessed high spatial resolution image is input as the input image to the 1st Conv3*3 convolution layer. The output of the 1st Conv3*3 convolution layer is activated by the Relu activation function and enters the 1st downsampling layer and the 1st snake convolution layer at the same time. The output of the 1st downsampling layer enters the 2nd Conv3*3 convolution layer. The output of the 2nd Conv3*3 convolution layer is activated by the Relu activation function and enters the 2nd downsampling layer and the 2nd snake convolution layer at the same time. The output of downsampling layer No. 2 enters Conv3*3 convolution layer No. 3, the output of Conv3*3 convolution layer No. 3 enters upsampling layer No. 1 after being activated by Relu activation function, the output of upsampling layer No. 1 and the output of snake convolution layer No. 2 enter splicing layer No. 1 at the same time, the output of splicing layer No. 1 enters Conv3*3 convolution layer No. 4, the output of Conv3*3 convolution layer No. 4 enters upsampling layer No. 2 after being activated by Relu activation function, the output of upsampling layer No. 2 and the output of snake convolution layer No. 1 enter splicing layer No. 2 at the same time, the output of splicing layer No. 2 enters Conv3*3 convolution layer No. 5, the output of Conv3*3 convolution layer No. 5 enters classification layer after being activated by Relu activation function, and the output of classification layer is output after being activated by activation function sigmoid.

5. The intelligent water intake device for direct drinking water terminal according to claim 1 is characterized in that: The device also includes a sterilization unit, which uses ultraviolet sterilization to perform terminal security disinfection.

6. The intelligent water intake device for direct drinking water terminal according to claim 1 is characterized in that: The device also includes a metering unit, which is used to measure the water flowing through the pipeline and send it to the control unit.

7. The intelligent water intake device for direct drinking water terminal according to claim 1 is characterized in that: The device also includes a prepayment unit. The control unit counts the water consumption according to the metering unit, and displays the water fee and payment method to remind the user to pay.

8. The intelligent water intake device for direct drinking water terminal according to claim 1 is characterized in that: The device also includes a data transmission module, and the control unit is used to transmit the water use information to other terminals through the data transmission unit.

Images