A solar-powered sewage purification cloud intelligent control system

Abstract

The present invention discloses a solar sewage purification cloud intelligent control system, comprising: a photovoltaic panel electrical control mechanism, which is used to adjust the voltage and current output by the photovoltaic panel; an energy storage mechanism, which is used to store the energy generated by the photovoltaic panel; a DC inverter mechanism, which is used to convert the DC voltage generated by the photovoltaic panel and the energy of the energy storage mechanism into an AC voltage, so as to provide energy supply for the entire system; a liquid level sensor mechanism, which is used to detect the liquid level in the sewage treatment pool; a water quality sensor mechanism, which is used to detect the water quality at different liquid levels in the sewage treatment pool; a current sensor, which is used to detect the current of a lift pump and an air pump; and an upper computer automatically adjusts the lift pump regulator and the air pump regulator according to the detection data, so as to achieve automatic control of water inlet and outlet and gas introduction in the sewage treatment pool, facilitate better control of oxygen introduction in the sewage treatment pool, and ensure efficient treatment of sewage in the sewage treatment pool.

Description

Technical Field

[0001] The present invention relates to the technical field of sewage treatment, and in particular to a solar sewage purification cloud intelligent control system. Background Art

[0002] The sewage treatment control system is an integrated hardware and software system used to monitor, control and optimize the sewage treatment process. It obtains data from sewage treatment facilities through sensors and automatically controls the treatment process through controllers and actuators to achieve supervision and optimization of sewage treatment effects, process parameters and energy consumption.

[0003] In the existing sewage treatment control system, the discharge of sewage and the addition of sewage to be treated during the sewage treatment process need to be controlled by personnel according to the purification status, which is time-consuming and labor-intensive. It is difficult to timely and effectively adjust the purification and discharge of sewage by the purification mechanism according to the sewage treatment status. At the same time, it is also difficult to remotely upgrade and maintain the control program of the PLC control module. The power supply of the equipment needs to be taken from the power grid, and the distribution of the power grid on the site must be taken into account during site selection and construction, which makes the design of the station have certain limitations. Summary of the invention

[0004] The purpose of the present invention is to provide a solar sewage purification cloud intelligent control system to solve the following technical problems:

[0005] The existing sewage treatment control system is difficult to timely and effectively adjust the purification and discharge of sewage by the purification mechanism according to the sewage treatment status. At the same time, it is difficult to remotely upgrade and maintain the control program of the PLC control module. Moreover, most village and town sewage treatment sites are deployed in the field, and the operation of conventional systems relies on the power grid, which makes it difficult to select a site for equipment construction and deployment. The electricity bills generated by the long-term operation of the equipment increase the cost burden of villages and towns.

[0006] The purpose of the present invention can be achieved through the following technical solutions:

[0007] A solar sewage purification cloud intelligent control system, comprising:

[0008] Photovoltaic panel electrical control mechanism, used to adjust the voltage and current output by the photovoltaic panel;

[0009] An energy storage mechanism for storing energy generated by photovoltaic panels;

[0010] The DC inverter mechanism is used to convert the DC voltage generated by the photovoltaic panels and the energy of the energy storage mechanism into AC voltage to provide energy supply for the entire system;

[0011] A liquid level sensing mechanism, used to detect the liquid level in the sewage treatment tank;

[0012] A water quality sensing mechanism is used to detect the water quality at different liquid levels in the sewage treatment tank;

[0013] A current sensor is used to detect the current of the lift pump and the air pump;

[0014] Flow sensors are used to detect the flow rates flowing into and out of the sewage treatment pool;

[0015] A temperature sensing mechanism is used to detect the water temperature at different liquid levels in the sewage treatment tank;

[0016] A lift pump regulator, used to regulate the lift pump to inject the sewage to be treated into the sewage treatment tank;

[0017] An air pump regulator is used to adjust the air pump to inject gas into the sewage treatment tank;

[0018] Remote communication module, used to transmit the detection data of liquid level sensor mechanism, water quality sensor mechanism, current sensor and flow sensor to the terminal server in real time, and store and analyze the data in the background of the server;

[0019] A PLC control module is used to transmit the detection data of the liquid level sensor mechanism, the water quality sensor mechanism, the current sensor and the flow sensor to the host computer, and adjust the lift pump regulator and the air pump regulator according to the data sent back by the host computer;

[0020] The ARM module is used to remotely perform OTA program upgrades and vulnerability repairs on the control program of the PLC control module through the remote communication module.

[0021] As a further solution of the present invention: the host computer performs deep learning on the detection data of historical pollution status through a convolutional neural network, obtains the corresponding pollution status according to the real-time detection data, and generates adjustment data for the lift pump regulator and the air pump regulator according to the pollution status. The energy for the operation of the equipment is generated by photovoltaic panels and stored by energy storage mechanisms. The DC inverter converts the DC voltage of the photovoltaic panels and the energy storage mechanism into AC voltage to provide energy for the system operation.

[0022] As a further solution of the present invention: the water quality sensing mechanism is provided in a plurality, and the plurality of water quality sensing mechanisms are evenly arranged at the lower liquid level layer, the middle liquid level layer and the upper liquid level layer of the sewage treatment tank;

[0023] The water quality sensing mechanism includes: a water quality sensor and an underwater camera, wherein the water quality sensor is used to detect water quality data of different liquid level layers in the sewage treatment pool, and the underwater camera is used to collect underwater images of different liquid level layers in the sewage treatment pool;

[0024] Among them, the sewage treatment pool is divided into three liquid level layers according to the height of the pool. The lower liquid level layer is located at one-third of the depth of the bottom end of the sewage treatment pool, the middle liquid level layer is located at one-third of the depth of the middle part of the sewage treatment pool, and the upper liquid level layer is located at one-third of the depth of the top end of the sewage treatment pool.

[0025] As a further solution of the present invention: the host computer performs deep learning on the detection data of historical pollution status through a convolutional neural network, including the following steps:

[0026] Obtaining historical data of water quality and corresponding underwater images of the lower liquid level layer, the middle liquid level layer, and the upper liquid level layer, as well as the corresponding pollution status when the historical data was collected;

[0027] Preprocessing historical data of water quality and corresponding underwater images;

[0028] Through the convolutional neural network, according to the water quality of the lower liquid level layer, the middle liquid level layer and the upper liquid level layer in different pollution states and the corresponding historical data of underwater images, the pollution state recognition model for the lower liquid level layer, the pollution state recognition model for the middle liquid level layer and the pollution state recognition model for the upper liquid level layer are trained respectively;

[0029] As a further solution of the present invention: preprocessing the historical data of water quality and corresponding underwater images includes the following steps:

[0030] Standardize the water quality data of the same time period in the historical data;

[0031] Denoise and enhance the image data in the historical data, and randomly group the image data of the same liquid level layer in the same time period, randomly assign 3 to 5 image data to each group, splice the image data in each group by random scaling and random cropping, and combine the images of each group into a combined image;

[0032] The obtained standardized water quality data and combined images are the pre-processed water quality data and image data.

[0033] As a further solution of the present invention: training a pollution state recognition model for the lower liquid level layer, a pollution state recognition model for the middle liquid level layer, and a pollution state recognition model for the upper liquid level layer, including:

[0034] The water quality of the lower liquid level layer, the middle liquid level layer and the upper liquid level layer and the historical data of the corresponding underwater images, as well as the pollution status data corresponding to the historical data are divided into a training set and a test set, and the preprocessed data is added to the training set;

[0035] The training set data are respectively input into the pollution state recognition model of the corresponding liquid level layer for training;

[0036] Respectively train a pollution state recognition model for the lower liquid level layer, a pollution state recognition model for the middle liquid level layer, and a pollution state recognition model for the upper liquid level layer;

[0037] Input the test set data into the pollution state recognition model of the corresponding liquid level layer for training, and obtain the corresponding training weights;

[0038] The corresponding training weights are input into the corresponding pollution state recognition model to make the model converge, and a pollution state recognition model for the lower liquid level layer, a pollution state recognition model for the middle liquid level layer and a pollution state recognition model for the upper liquid level layer are obtained.

[0039] As a further solution of the present invention: the host computer obtains the corresponding pollution state according to the real-time detection data, and generates the adjustment data of the lift pump regulator and the air pump regulator according to the pollution state, including the following steps:

[0040] The collected water quality of the lower liquid level layer, the middle liquid level layer and the upper liquid level layer and the corresponding real-time data of the underwater image are respectively input into the pollution state recognition model for the lower liquid level layer, the pollution state recognition model for the middle liquid level layer and the pollution state recognition model for the upper liquid level layer;

[0041] The pollution state identification model for the lower liquid level layer, the pollution state identification model for the middle liquid level layer and the pollution state identification model for the upper liquid level layer respectively output the pollution state of the lower liquid level layer, the pollution state of the middle liquid level layer and the pollution state of the upper liquid level layer;

[0042] When the pollution status meets the discharge standard, the sewage is discharged, and after the discharge is completed, the lifting pump regulator is controlled to re-inject the sewage to be treated into the sewage treatment tank;

[0043] When the pollution status does not meet the emission standards, the air pump regulator is controlled to adjust the air pump to inject gas into the sewage treatment pool.

[0044] As a further solution of the present invention: when the pollution state meets the discharge standard, the sewage is discharged, comprising the following steps:

[0045] Determine whether the pollution state of the lower liquid level layer, the pollution state of the middle liquid level layer and the pollution state of the upper liquid level layer meet the sewage purification and discharge standards;

[0046] If the pollution status of all liquid level layers meets the sewage purification and discharge standards, the lifting pump regulator is controlled to discharge sewage from all liquid level layers;

[0047] If the pollution state of the middle liquid level layer and the pollution state of the upper liquid level layer both meet the sewage purification and discharge standards, the lifting pump regulator is controlled to discharge sewage from the middle liquid level layer and the upper liquid level layer;

[0048] As a further solution of the present invention: when the pollution state does not meet the emission standard, the air pump regulator is controlled to adjust the air pump to inject gas into the sewage treatment pool, including the following steps:

[0049] Determine the pollution state of the lower liquid level layer, the pollution state of the middle liquid level layer and the pollution state of the upper liquid level layer;

[0050] For the liquid level layer that does not meet the sewage purification discharge standard, the air pump regulator is controlled to adjust the air pump of the corresponding liquid level layer in the sewage treatment pool to inject gas into the sewage treatment pool;

[0051] The air pump regulator injects gas into the sewage treatment pool by regulating the air pumps of the lower liquid level layer, the middle liquid level layer and the upper liquid level layer in the sewage treatment pool.

[0052] As a further solution of the present invention: also include:

[0053] A power supply module is equipped with an AC-DC power supply end and a DC-DC power supply end, and supplies power to a liquid level sensor mechanism, a water quality sensor mechanism, a current sensor, a temperature sensor mechanism, a flow sensor, a lift pump regulator, an air pump regulator and a host computer through an LDO chip. The power supply module supports 220V / AC power supply or 24V / DC power supply.

[0054] Beneficial effects of the present invention:

[0055] The present invention transmits the detection data of the liquid level sensing mechanism, the water quality sensing mechanism, the current sensor and the flow sensor to the host computer through the PLC control module, and adjusts the lift pump regulator and the air pump regulator according to the data sent back by the host computer. The host computer automatically adjusts the lift pump regulator and the air pump regulator according to the detection data, so as to automatically control the water inlet and outlet and the gas introduction in the sewage treatment pool, facilitate better control of the oxygen introduction in the sewage treatment pool, and ensure the efficient treatment of sewage in the sewage treatment pool.

[0056] The present invention generates direct current electricity through photovoltaic panels, stores the energy through an energy storage mechanism, and converts the direct current voltage into alternating current voltage through a direct current inverter mechanism, thereby achieving the independence of system energy. The power supply of the equipment is no longer dependent on the traditional power grid, and the equipment can operate independently in areas that cannot be connected to the power grid. Solar energy is a continuous and free energy source, so the equipment does not need to pay extra electricity bills when it is running, which solves the difficulties of equipment operation and management in villages and towns.

[0057] The present invention uses highly integrated integrated circuits to complete the electrical connection between each module, which not only greatly reduces the use of cables between modules, but also reduces the volume of equipment, improves the stability of the equipment, and makes installation simpler and more convenient. The remote communication module can remotely collect data and control the system. At the same time, the ARM module remotely upgrades the control program of the PLC control module through OTA and repairs vulnerabilities through the remote communication module, which is convenient for remote upgrading and maintenance of the control program. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] The present invention will be further described below in conjunction with the accompanying drawings.

[0059] Figure 1 It is a schematic diagram of the structure of the system of the present invention. DETAILED DESCRIPTION

[0060] 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.

[0061] See also Figure 1 As shown, the present invention is a solar sewage purification cloud intelligent control system, comprising:

[0062] Photovoltaic panel electrical control mechanism, used to adjust the voltage and current output by the photovoltaic panel;

[0063] An energy storage mechanism for storing the energy generated by the photovoltaic panels;

[0064] The DC inverter mechanism is used to convert the DC voltage generated by the photovoltaic panels and the energy of the energy storage mechanism into AC voltage to provide energy supply for the entire system;

[0065] A liquid level sensing mechanism, used to detect the liquid level in the sewage treatment tank;

[0066] A water quality sensing mechanism is used to detect the water quality at different liquid levels in the sewage treatment tank;

[0067] A current sensor is used to detect the current of the lift pump and the air pump;

[0068] Flow sensors are used to detect the flow rates flowing into and out of the sewage treatment pool;

[0069] A temperature sensing mechanism is used to detect the water temperature at different liquid levels in the sewage treatment tank;

[0070] A lift pump regulator, used to regulate the lift pump to inject the sewage to be treated into the sewage treatment tank;

[0071] An air pump regulator is used to adjust the air pump to inject gas into the sewage treatment tank;

[0072] Remote communication module, used to transmit the detection data of liquid level sensor mechanism, water quality sensor mechanism, current sensor and flow sensor to the terminal server in real time, and store and analyze the data in the background of the server;

[0073] A PLC control module is used to transmit the detection data of the liquid level sensor mechanism, the water quality sensor mechanism, the current sensor and the flow sensor to the host computer, and adjust the lift pump regulator and the air pump regulator according to the data sent back by the host computer;

[0074] The ARM module is used to remotely perform OTA program upgrades and vulnerability repairs on the control program of the PLC control module through the remote communication module.

[0075] Specifically, the detection data of the liquid level sensor mechanism, water quality sensor mechanism, current sensor and flow sensor are transmitted to the host computer through the PLC control module, and the lift pump regulator and the air pump regulator are adjusted according to the data sent back by the host computer. The host computer automatically adjusts the lift pump regulator and the air pump regulator according to the detection data, so as to automatically control the water inlet and outlet and the gas introduction in the sewage treatment pool, so as to better control the oxygen introduction in the sewage treatment pool and ensure the efficient treatment of sewage in the sewage treatment pool.

[0076] Through high integration and the use of integrated circuits, the electrical connection between each module is completed, which not only greatly reduces the use of cables between modules, but also reduces the size of the equipment, improves the stability of the equipment, and makes installation simpler and more convenient.

[0077] The system can be remotely controlled and data collected through the remote communication module. At the same time, the ARM module can remotely perform OTA program upgrades and vulnerability repairs on the control program of the PLC control module through the remote communication module, making it easier to remotely upgrade and maintain the control program.

[0078] As a further solution of the present invention: the upper computer performs deep learning on the detection data of historical pollution status through a convolutional neural network, obtains the corresponding pollution status according to the real-time detection data, and generates adjustment data for the lift pump regulator and the air pump regulator according to the pollution status.

[0079] Specifically, the detection data of historical pollution states are deeply learned through convolutional neural networks, the corresponding pollution states are obtained according to the real-time detection data, and the adjustment data of the lift pump regulator and the air pump regulator are generated according to the pollution states; by learning from the historical pollution data, new pollution states can be accurately predicted and classified.

[0080] As a further solution of the present invention: a plurality of water quality sensing mechanisms are provided, and the plurality of water quality sensing mechanisms are evenly arranged at the lower liquid level layer, the middle liquid level layer and the upper liquid level layer of the sewage treatment tank;

[0081] The water quality sensing mechanism includes: a water quality sensor and an underwater camera. The water quality sensor is used to detect water quality data of different liquid level layers in the sewage treatment pool, and the underwater camera is used to collect underwater images of different liquid level layers in the sewage treatment pool;

[0082] Among them, the sewage treatment pool is divided into three liquid level layers according to the height of the pool. The lower liquid level layer is located at one-third of the depth of the bottom of the sewage treatment pool, the middle liquid level layer is located at one-third of the depth of the middle of the sewage treatment pool, and the upper liquid level layer is located at one-third of the depth of the top of the sewage treatment pool.

[0083] Specifically, by setting up water quality sensing mechanisms at the lower liquid level layer, the middle liquid level layer and the upper liquid level layer of the sewage treatment tank, it is convenient to monitor the state of sewage at different liquid level layers in the sewage treatment tank, facilitate better evaluation of the progress of sewage treatment, and facilitate efficient treatment of sewage by collecting the purification conditions inside the sewage treatment tank. The water quality sensing mechanism includes a water quality sensor and an underwater camera. The water quality sensors and underwater cameras located at different underwater liquid level layers can collect water quality data and underwater images of different liquid level layers in the sewage treatment tank, so as to more comprehensively collect the internal purification conditions of the sewage treatment tank.

[0084] As a further solution of the present invention: the host computer performs deep learning on the detection data of historical pollution status through a convolutional neural network, including the following steps:

[0085] Obtaining historical data of water quality and corresponding underwater images of the lower liquid level layer, the middle liquid level layer, and the upper liquid level layer, as well as the corresponding pollution status when the historical data was collected;

[0086] Preprocessing historical data of water quality and corresponding underwater images;

[0087] Through convolutional neural networks, according to the water quality of the lower liquid level layer, middle liquid level layer and upper liquid level layer in different pollution states and the corresponding historical data of underwater images, the pollution state recognition model for the lower liquid level layer, the pollution state recognition model for the middle liquid level layer and the pollution state recognition model for the upper liquid level layer are trained respectively.

[0088] Specifically, the pollution state recognition model for the lower liquid level layer, the pollution state recognition model for the middle liquid level layer, and the pollution state recognition model for the upper liquid level layer are trained respectively; this helps to improve the generalization ability of the model and improve the detection and recognition effect of the model on data of different liquid level layers.

[0089] As a further solution of the present invention: preprocessing the historical data of water quality and corresponding underwater images includes the following steps:

[0090] Standardize the water quality data of the same time period in the historical data;

[0091] Denoise and enhance the image data in the historical data, and randomly group the image data of the same liquid level layer in the same time period, randomly assign 3 to 5 image data to each group, splice the image data in each group by random scaling and random cropping, and combine the images of each group into a combined image;

[0092] The obtained standardized water quality data and combined images are the pre-processed water quality data and image data.

[0093] Specifically, denoising and image enhancement are performed through image data in historical data, and image data of the same liquid level layer in the same time period are randomly grouped, 3 to 5 image data are randomly assigned to each group, and the image data in each group are spliced ​​by random scaling and random cropping, and the images of each group are combined into a combined image; different targets may be blocked or overlapped in a single image, causing mutual interference. Combining each group of images of the same liquid level layer into a combined image can provide more mutual influence between targets, so that the model can better learn to deal with these scenes. Reduce the risk of model overfitting; combining multiple images in the same liquid level layer group into a combined image is convenient for providing more diverse training data for the model, so that the trained model will have more generalization ability in dealing with diverse scenes and targets.

[0094] As a further solution of the present invention: training a pollution state recognition model for the lower liquid level layer, a pollution state recognition model for the middle liquid level layer, and a pollution state recognition model for the upper liquid level layer, including:

[0095] The water quality of the lower liquid level layer, the middle liquid level layer and the upper liquid level layer and the historical data of the corresponding underwater images, as well as the pollution status data corresponding to the historical data are divided into a training set and a test set, and the preprocessed data is added to the training set;

[0096] The training set data are respectively input into the pollution state recognition model of the corresponding liquid level layer for training;

[0097] Respectively train a pollution state recognition model for the lower liquid level layer, a pollution state recognition model for the middle liquid level layer, and a pollution state recognition model for the upper liquid level layer;

[0098] Input the test set data into the pollution state recognition model of the corresponding liquid level layer for training, and obtain the corresponding training weights;

[0099] The corresponding training weights are input into the corresponding pollution state recognition model to make the model converge, and a pollution state recognition model for the lower liquid level layer, a pollution state recognition model for the middle liquid level layer and a pollution state recognition model for the upper liquid level layer are obtained.

[0100] Specifically, by combining each group of pictures of the same liquid level layer into a combined picture, the combined picture obtained is used as a training set for training, so as to provide the model with more diverse training data. The trained model will be more generalizable in dealing with diverse scenes and targets, and the image types of training samples are increased, thereby reducing the risk of model overfitting. By providing more training samples, the model can better learn and generalize to new data. The input of multiple data enables the model to have better generalization ability and improves the robustness of the model. Even if it is not verified by the validation set, the model can be directly tested and trained to converge, which simplifies the model training process and ensures the detection and recognition effect of the trained model on different liquid level layer data.

[0101] As a further solution of the present invention: the host computer obtains the corresponding pollution state according to the real-time detection data, and generates the adjustment data of the lift pump regulator and the air pump regulator according to the pollution state, including the following steps:

[0102] The collected water quality of the lower liquid level layer, the middle liquid level layer and the upper liquid level layer and the corresponding real-time data of the underwater image are respectively input into the pollution state recognition model for the lower liquid level layer, the pollution state recognition model for the middle liquid level layer and the pollution state recognition model for the upper liquid level layer;

[0103] The pollution state identification model for the lower liquid level layer, the pollution state identification model for the middle liquid level layer and the pollution state identification model for the upper liquid level layer respectively output the pollution state of the lower liquid level layer, the pollution state of the middle liquid level layer and the pollution state of the upper liquid level layer;

[0104] When the pollution status meets the discharge standard, the sewage is discharged, and after the discharge is completed, the lifting pump regulator is controlled to re-inject the sewage to be treated into the sewage treatment tank;

[0105] When the pollution status does not meet the emission standards, the air pump regulator is controlled to adjust the air pump to inject gas into the sewage treatment pool.

[0106] As a further solution of the present invention: when the pollution state meets the discharge standard, the sewage is discharged, comprising the following steps:

[0107] Determine whether the pollution state of the lower liquid level layer, the pollution state of the middle liquid level layer and the pollution state of the upper liquid level layer meet the sewage purification and discharge standards;

[0108] If the pollution status of all liquid level layers meets the sewage purification and discharge standards, the lifting pump regulator is controlled to discharge sewage from all liquid level layers;

[0109] If the pollution state of the middle liquid level layer and the pollution state of the upper liquid level layer both meet the sewage purification and discharge standards, the lift pump regulator is controlled to discharge the sewage from the middle liquid level layer and the upper liquid level layer.

[0110] Specifically, when the pollution status of the middle liquid level layer and the pollution status of the upper liquid level layer both meet the sewage purification and discharge standards, the lifting pump regulator is controlled to discharge the sewage from the middle liquid level layer and the upper liquid level layer, thereby accelerating the discharge of the sewage purified to the discharge standards and accelerating the purification efficiency of the sewage treatment pool.

[0111] As a further solution of the present invention: when the pollution state does not meet the emission standard, the air pump regulator is controlled to adjust the air pump to inject gas into the sewage treatment pool, including the following steps:

[0112] Determine the pollution state of the lower liquid level layer, the pollution state of the middle liquid level layer and the pollution state of the upper liquid level layer;

[0113] For the liquid level layer that does not meet the sewage purification discharge standard, the air pump regulator is controlled to adjust the air pump of the corresponding liquid level layer in the sewage treatment pool to inject gas into the sewage treatment pool;

[0114] Among them, the air pump regulator injects gas into the sewage treatment pool by adjusting the air pumps of the lower liquid level layer, the middle liquid level layer and the upper liquid level layer in the sewage treatment pool.

[0115] As a further solution of the present invention: also include:

[0116] The power module is equipped with an AC-DC power supply end and a DC-DC power supply end, and supplies power to the liquid level sensor mechanism, water quality sensor mechanism, current sensor, flow sensor, temperature sensor mechanism, lift pump regulator, air pump regulator and host computer through an LDO chip. The power module supports 220V / AC power supply or 24V / DC power supply.

[0117] Specifically, the power module supports 220V / AC power supply or 24V / DC power supply, so that the system can adapt to the requirements of different working conditions.

[0118] In the description of the present invention, it should be understood that the terms "upper", "lower", "left", "right", etc. indicate directions or positional relationships based on the directions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, and a specific direction structure and operation, and therefore, cannot be understood as a limitation on the present invention. In addition, "first" and "second" are only for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, unless otherwise specified, "multiple" means two or more.

[0119] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", etc. should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be an indirect connection through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0120] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A solar sewage purification cloud intelligent control system, characterized in that: include: Photovoltaic panel electrical control mechanism, used to adjust the voltage and current output by the photovoltaic panel; An energy storage mechanism for storing energy generated by photovoltaic panels; The DC inverter mechanism is used to convert the DC voltage generated by the photovoltaic panels and the energy of the energy storage mechanism into AC voltage to provide energy supply for the entire system; A liquid level sensing mechanism, used to detect the liquid level in the sewage treatment tank; A water quality sensing mechanism is used to detect the water quality at different liquid levels in the sewage treatment tank; A current sensor is used to detect the current of the lift pump and the air pump; Flow sensors are used to detect the flow rates flowing into and out of the sewage treatment pool; A temperature sensing mechanism is used to detect the water temperature at different liquid levels in the sewage treatment tank; A lift pump regulator, used to regulate the lift pump to inject the sewage to be treated into the sewage treatment tank; An air pump regulator is used to adjust the air pump to inject gas into the sewage treatment tank; Remote communication module, used to transmit the detection data of liquid level sensor mechanism, water quality sensor mechanism, current sensor and flow sensor to the terminal server in real time, and store and analyze the data in the background of the server; A PLC control module is used to transmit the detection data of the liquid level sensor mechanism, the water quality sensor mechanism, the current sensor and the flow sensor to the host computer, and adjust the lift pump regulator and the air pump regulator according to the data sent back by the host computer; ARM module, used to remotely perform OTA program upgrades and vulnerability repairs on the control program of the PLC control module through the remote communication module; The host computer performs deep learning on the detection data of historical pollution status through a convolutional neural network, obtains the corresponding pollution status according to the real-time detection data, and generates adjustment data for the lift pump regulator and the air pump regulator according to the pollution status. The energy for the operation of the equipment is generated by the photovoltaic panel and the energy storage mechanism stores the energy. The DC inverter converts the DC voltage of the photovoltaic panel and the energy storage mechanism into AC voltage to provide energy for the operation of the system; The water quality sensing mechanisms are provided in a plurality, and the plurality of water quality sensing mechanisms are evenly arranged at the lower liquid level layer, the middle liquid level layer and the upper liquid level layer of the sewage treatment tank; The water quality sensing mechanism includes: a water quality sensor and an underwater camera, wherein the water quality sensor is used to detect water quality data of different liquid level layers in the sewage treatment pool, and the underwater camera is used to collect underwater images of different liquid level layers in the sewage treatment pool; The sewage treatment pool is divided into three liquid level layers according to the height of the pool, the lower liquid level layer is located at one-third of the depth of the bottom end of the sewage treatment pool, the middle liquid level layer is located at one-third of the depth of the middle part of the sewage treatment pool, and the upper liquid level layer is located at one-third of the depth of the top end of the sewage treatment pool; The host computer obtains the corresponding pollution state according to the real-time detection data, and generates the adjustment data of the lift pump regulator and the air pump regulator according to the pollution state, including the following steps: The collected water quality of the lower liquid level layer, the middle liquid level layer and the upper liquid level layer and the corresponding real-time data of the underwater image are respectively input into the pollution state recognition model for the lower liquid level layer, the pollution state recognition model for the middle liquid level layer and the pollution state recognition model for the upper liquid level layer; The pollution state identification model for the lower liquid level layer, the pollution state identification model for the middle liquid level layer and the pollution state identification model for the upper liquid level layer respectively output the pollution state of the lower liquid level layer, the pollution state of the middle liquid level layer and the pollution state of the upper liquid level layer; When the pollution status meets the discharge standard, the sewage is discharged, and after the discharge is completed, the lifting pump regulator is controlled to re-inject the sewage to be treated into the sewage treatment tank; When the pollution state does not meet the emission standards, the air pump regulator is controlled to adjust the air pump to inject gas into the sewage treatment pool; When the pollution status meets the discharge standards, the sewage is discharged, including the following steps: Determine whether the pollution state of the lower liquid level layer, the pollution state of the middle liquid level layer and the pollution state of the upper liquid level layer meet the sewage purification and discharge standards; If the pollution status of all liquid level layers meets the sewage purification and discharge standards, the lifting pump regulator is controlled to discharge sewage from all liquid level layers; If the pollution state of the middle liquid level layer and the pollution state of the upper liquid level layer both meet the sewage purification and discharge standards, the lifting pump regulator is controlled to discharge sewage from the middle liquid level layer and the upper liquid level layer; When the pollution state does not meet the emission standards, the air pump regulator is controlled to adjust the air pump to inject gas into the sewage treatment pool, including the following steps: Determine the pollution state of the lower liquid level layer, the pollution state of the middle liquid level layer and the pollution state of the upper liquid level layer; For the liquid level layer that does not meet the sewage purification discharge standard, the air pump regulator is controlled to adjust the air pump of the corresponding liquid level layer in the sewage treatment pool to inject gas into the sewage treatment pool; The air pump regulator injects gas into the sewage treatment pool by regulating the air pumps of the lower liquid level layer, the middle liquid level layer and the upper liquid level layer in the sewage treatment pool.

2. According to claim 1, a solar sewage purification cloud intelligent control system is characterized in that: The host computer performs deep learning on the detection data of historical pollution status through a convolutional neural network, including the following steps: Obtaining historical data of water quality and corresponding underwater images of the lower liquid level layer, the middle liquid level layer, and the upper liquid level layer, as well as the corresponding pollution status when the historical data was collected; Preprocessing historical data of water quality and corresponding underwater images; Through convolutional neural networks, according to the water quality of the lower liquid level layer, middle liquid level layer and upper liquid level layer in different pollution states and the corresponding historical data of underwater images, the pollution state recognition model for the lower liquid level layer, the pollution state recognition model for the middle liquid level layer and the pollution state recognition model for the upper liquid level layer are trained respectively.

3. According to claim 2, a solar sewage purification cloud intelligent control system is characterized in that: The historical data of water quality and corresponding underwater images are preprocessed, including the following steps: Standardize the water quality data of the same time period in the historical data; Denoise and enhance the image data in the historical data, and randomly group the image data of the same liquid level layer in the same time period, randomly assign 3 to 5 image data to each group, splice the image data in each group by random scaling and random cropping, and combine the images of each group into a combined image; The obtained standardized water quality data and combined images are the pre-processed water quality data and image data.

4. According to claim 2, a solar sewage purification cloud intelligent control system is characterized in that: Training a pollution state recognition model for the lower liquid level layer, a pollution state recognition model for the middle liquid level layer, and a pollution state recognition model for the upper liquid level layer, including: The water quality of the lower liquid level layer, the middle liquid level layer and the upper liquid level layer and the historical data of the corresponding underwater images, as well as the pollution status data corresponding to the historical data are divided into a training set and a test set, and the preprocessed data is added to the training set; The training set data are respectively input into the pollution state recognition model of the corresponding liquid level layer for training; Respectively train a pollution state recognition model for the lower liquid level layer, a pollution state recognition model for the middle liquid level layer, and a pollution state recognition model for the upper liquid level layer; Input the test set data into the pollution state recognition model of the corresponding liquid level layer for training, and obtain the corresponding training weights; The corresponding training weights are input into the corresponding pollution state recognition model to make the model converge, and a pollution state recognition model for the lower liquid level layer, a pollution state recognition model for the middle liquid level layer and a pollution state recognition model for the upper liquid level layer are obtained.

5. A solar sewage purification cloud intelligent control system according to any one of claims 1 to 4, characterized in that: Also includes: The power module is equipped with an AC-DC power supply end and a DC-DC power supply end, and supplies power to a liquid level sensor mechanism, a water quality sensor mechanism, a current sensor, a flow sensor, a temperature sensor mechanism, a lift pump regulator, an air pump regulator and a host computer through an LDO chip. The power module supports 220V / AC power supply or 24V / DC power supply.

Images