A method and device for automatically controlling an ecological cabin

Abstract

The present application discloses an automatic control method and device for an ecological cabin, and relates to the technical field of electrical digital data processing. The method utilizes that yellowing, withering, leaf shedding, overall wilting and death of plant leaves are all shrinkage processes caused by water reduction, and its intuitive visual effect is the reduction of the visual area of ​​the plant at multiple viewing angles. The plant can show this characteristic when it is initially short of water, and as the degree of water shortage increases, the visual area will continue to decrease, that is, the degree of water shortage and the visual area are positively correlated, so that the present application can capture this characteristic through at least two viewing angles, and there is no need to identify the plant variety, and only the degree of water shortage needs to be judged by the visual area. The method is suitable for plants of different colors, and the oxygenation component is turned on when the visual area is reduced at multiple viewing angles to prevent the plant from being short of water for a long time or being redundantly irrigated.

Description

Technical Field

[0001] The present application relates to the technical field of electronic digital data processing, and in particular to an automatic control method and device for an ecological cabin. Background Art

[0002] The eco-cabin is a plant cultivation device placed in a confined space indoors or hung on a curtain wall. It is used to provide fresh air to the interior and increase greenery and ecological sensory elements. Different plants can be cultivated by adjusting the temperature, humidity, wind speed, etc. of the eco-cabin. The eco-cabin is currently the mainstream greening and oxygenation method for indoor public environments and curtain walls.

[0003] Eco-cabins have been widely used in the interiors or curtain walls of modern large buildings to improve the indoor environment. However, the maintenance of the eco-cabins is to cultivate the plants inside through regular artificial irrigation. Due to the different habits of plants, and the fact that most staff of large buildings have not formulated corresponding irrigation plans for different varieties of plants, different plants may be in a state of water shortage or waterlogging. That is, the staff under-irrigate or redundantly irrigate different plants at the same time, which is not conducive to the healthy growth of plants in the eco-cabins. Summary of the invention

[0004] The main purpose of the present application is to provide an automatic control method and device for an eco-cabin, so as to solve the problem in the prior art that plant irrigation in the eco-cabin is not conducive to the healthy growth of plants in the eco-cabin.

[0005] In order to achieve the above objectives, this application provides the following technical solutions:

[0006] An automatic control method for an ecological cabin, the ecological cabin comprising a hollow transparent column covered by an air circulation component and an oxygenation component in sequence from top to bottom, a substrate laid on the oxygenation component, and healthy plants located in the hollow transparent column and planted on the substrate, the automatic control method comprising:

[0007] Step S1, acquiring a plurality of visual images of the healthy plant from at least two perspectives based on a preset time period;

[0008] Step S2, obtaining the boundary coordinates of each visual image based on a boundary extraction algorithm;

[0009] Step S3, packing all boundary coordinates of a visual image into a coordinate data set based on the same viewing angle;

[0010] Step S4, training and learning all coordinate data sets through an extreme learning algorithm, and obtaining at least one predicted coordinate data set based on one perspective;

[0011] Step S5, obtaining the enclosed area of ​​all coordinate data sets and the predicted enclosed area of ​​all predicted coordinate data sets;

[0012] Step S6, obtaining a ratio value of the predicted enclosed area to the enclosed area based on the same viewing angle;

[0013] Step S7, determining whether the ratio value of each viewing angle is less than or equal to a preset area ratio, and defining the viewing angle whose ratio value is less than or equal to the preset area ratio as the focus viewing angle;

[0014] Step S8, determining whether the number of all concerned viewing angles is greater than or equal to a preset number threshold, if the number of all concerned viewing angles is greater than or equal to the preset number threshold, executing step S9;

[0015] Step S9, start the air circulation component and the oxygenation component.

[0016] As a further improvement of the present application, step S2, based on the boundary extraction algorithm, respectively obtains the boundary coordinates of each visual image, including:

[0017] Step S21, binarizing the current visual image to obtain a black and white visual image;

[0018] Step S22, defining grids with the same resolution according to the resolution of the visual image to divide the black and white visual image;

[0019] Step S23, respectively obtaining the RGB color value of each grid;

[0020] Step S24, assigning a value of 1 to a grid whose RGB color value is 0, 0, 0, and assigning a value of 0 to a grid whose RGB color value is 255, 255, 255;

[0021] Step S25, defining each grid and eight adjacent grids as a 3×3 window;

[0022] Step S26, traversing all grids through the 3×3 window with one grid as one step;

[0023] Step S27, based on all traversal results, delete the grids whose values ​​are all 1 and the grids whose values ​​are all 0 in the 3×3 window;

[0024] Step S28, obtaining the retained grid and defining it as a boundary;

[0025] Step S29, obtaining the coordinates of the boundary based on the pixel coordinates of the current visual image and defining them as the boundary coordinates.

[0026] As a further improvement of the present application, step S4, training and learning all coordinate data sets through an extreme learning algorithm, and obtaining at least one predicted coordinate data set based on one perspective, includes:

[0027] Step S10, packing all pixel color values ​​of a visual image into a color value data set;

[0028] Step S20, normalizing all color value data sets to obtain normalized data sets;

[0029] Step S30, dividing the normalized data set into a training set and a validation set according to a preset ratio;

[0030] Step S40, defining an extreme learning model according to the data dimension of the training set;

[0031] Step S50, training and learning the extreme learning model through the training set to obtain a prediction model;

[0032] Step S60: output the verification set to the prediction model, and obtain at least one prediction coordinate data set based on a viewing angle.

[0033] As a further improvement of the present application, step S50, training and learning the extreme learning model through the training set to obtain a prediction model, includes:

[0034] Step S541, define the training set as , the number of training sets is ;

[0035] in, , For the The coordinate values ​​of the normalized data set, for of A collection of n-dimensional vectors; , For the The color values ​​of the normalized dataset, for of A collection of dimensional vectors, with a subscript is the transposed matrix;

[0036] Step S542, defining the extreme learning model according to formula (1):

[0037] (1);

[0038] in, , is the first connection weight between the hidden layer and the output layer of the extreme learning model; is the number of nodes in the hidden layer; is the output value of the hidden layer, ; ; is the activation function; is the input layer of the extreme learning model and the hidden layer The second connection weight of the nodes; is the hidden layer The threshold of nodes;

[0039] Step S543, randomly generating the second connection weight and the threshold value by a nonlinear mapping function in a feature space based on the extreme learning model;

[0040] Step S544, obtaining the output value of the hidden layer by calculating the randomly generated second connection weight and the threshold;

[0041] Step S545, according to formula (2), the optimal solution of the first connection weight is solved by minimizing the approximate square error:

[0042] (2);

[0043] in, is the output matrix of the hidden layer; is the target matrix of the training sample; is the optimal solution; The output matrix The MP generalized inverse matrix, , The dimension is The set of weight vectors of ;

[0044] Step S546, obtaining the optimal solution and the second connection weight and threshold corresponding to the optimal solution and substituting them into the extreme learning model to obtain the prediction model.

[0045] As a further improvement of the present application, step S9, starting the air circulation component and the oxygenation component, includes:

[0046] Step S91, obtaining the humidity habits of the healthy plants through a preset strategy;

[0047] Step S92, obtaining the air humidity in the hollow transparent column through an external detection terminal;

[0048] Step S93, obtaining the humidity difference between the air humidity and the humidity habit, if the humidity difference is greater than zero, executing step S94; if the humidity difference is less than zero, executing step S95;

[0049] Step S94, increasing the output power of the air circulation component at a first preset adjustment ratio;

[0050] Step S95, reducing the output power of the air circulation component at a second preset adjustment ratio.

[0051] As a further improvement of the present application, step S9, starting the air circulation component and the oxygenation component, then includes:

[0052] Step S100, closing the oxygenation component based on a preset irrigation duration;

[0053] Step S200, repeating steps S1 to S8.

[0054] As a further improvement of the present application, step S9, starting the air circulation component and the oxygenation component, then includes:

[0055] Step S1000, obtaining the opening timestamps of the air circulation component and the oxygenation component and the closing timestamp of the oxygenation component;

[0056] Step S2000: sending the opening timestamp and the closing timestamp to an external receiving end.

[0057] In order to achieve the above objectives, this application also provides the following technical solutions:

[0058] An automatic control device for an eco-cabin, the automatic control device is applied to the automatic control method for the eco-cabin as described above, and the automatic control device comprises:

[0059] A visual image acquisition module, used for acquiring a plurality of visual images of the healthy plant from at least two viewing angles based on a preset time period;

[0060] A boundary coordinate acquisition module, used to respectively acquire the boundary coordinates of each visual image based on a boundary extraction algorithm;

[0061] A coordinate data set packaging module, used to package all boundary coordinates of a visual image into a coordinate data set based on the same viewing angle;

[0062] A predicted coordinate data set acquisition module, used to train and learn all coordinate data sets through an extreme learning algorithm, and obtain at least one predicted coordinate data set based on a perspective;

[0063] The enclosed area acquisition and prediction module is used to obtain the enclosed areas of all coordinate data sets and the predicted enclosed areas of all predicted coordinate data sets;

[0064] An enclosed area difference acquisition module, used for acquiring a ratio value between the predicted enclosed area and the enclosed area based on the same viewing angle;

[0065] The enclosed area difference judgment module is used to judge whether the ratio value of each viewing angle is less than or equal to the preset area ratio, and define the viewing angle whose ratio value is less than or equal to the preset area ratio as the focus viewing angle;

[0066] A module for determining the number of viewing angles of interest, used to determine whether the number of all viewing angles of interest is greater than or equal to a preset number threshold;

[0067] The air circulation component and the oxygenation component activation module is used to activate the air circulation component and the oxygenation component if the number of all the viewing angles of interest is greater than or equal to a preset number threshold.

[0068] In order to achieve the above objectives, this application also provides the following technical solutions:

[0069] An electronic device includes a processor and a memory coupled to the processor, wherein the memory stores program instructions executable by the processor; when the processor executes the program instructions stored in the memory, the automatic control method of the eco-cabin as described above is implemented.

[0070] To achieve the above objectives, this application also provides the following technical solutions:

[0071] A storage medium stores program instructions, which, when executed by a processor, can implement the automatic control method of the eco-cabin as described above.

[0072] The present application obtains several visual images of healthy plants from at least two perspectives based on a preset time period; obtains the boundary coordinates of each visual image based on a boundary extraction algorithm; packages all boundary coordinates of a visual image into a coordinate data set based on the same perspective; trains and learns all coordinate data sets through an extreme learning algorithm, and obtains at least one predicted coordinate data set based on one perspective; obtains the enclosed area of ​​all coordinate data sets and the predicted enclosed area of ​​all predicted coordinate data sets; obtains the ratio of the predicted enclosed area to the enclosed area based on the same perspective; determines whether the ratio value of each perspective is less than or equal to the preset area ratio, and defines the perspective with a ratio value less than or equal to the preset area ratio as a focus perspective; determines whether the number of all focus perspectives is greater than or equal to a preset number threshold; if the number of all focus perspectives is greater than or equal to the preset number threshold, turns on the air circulation component and the oxygen enrichment component. The present application utilizes the fact that yellowing, wilting, leaf shedding, overall wilting and death of plant leaves are all shrinkage processes caused by reduced water content, and its intuitive visual effect is the reduction in the visual area of ​​the plant at multiple viewing angles. The plant can exhibit this characteristic when it is initially short of water, and the visual area will continue to decrease as the degree of water shortage increases, that is, the degree of water shortage and the visual area are positively correlated, so that the present application can capture this characteristic through at least two viewing angles, and there is no need to identify the plant variety, and the degree of water shortage can be judged only by the visual area. It is suitable for plants of different colors, and the oxygenation component is turned on when the visual area is reduced at multiple viewing angles to prevent the plant from long-term water shortage or redundant irrigation, thereby ensuring the healthy growth of the plant. At the same time, the increased visual area during plant growth does not affect the entire process of the present application. Since the visual image of the plant is repeatedly acquired at intervals at the initial step, the growth characteristics will be continuously updated, and will not lead to inaccurate subsequent judgments. BRIEF DESCRIPTION OF THE DRAWINGS

[0073] Figure 1 A schematic diagram of the steps of an embodiment of the automatic control method of the eco-cabin of the present application;

[0074] Figure 2 This is a functional module diagram of an embodiment of the automatic control device of the eco-cabin of the present application;

[0075] Figure 3 This is a schematic diagram of the structure of an embodiment of the electronic device of the present application;

[0076] Figure 4 This is a schematic diagram of the structure of an embodiment of the storage medium of the present application. DETAILED DESCRIPTION

[0077] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0078] The terms "first", "second" and "third" in this application are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the number of indicated technical features. Therefore, the features defined as "first", "second" and "third" can explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "multiple" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined. All directional indications (such as up, down, left, right, front, back...) in the embodiments of this application are only used to explain the relative position relationship, movement, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication also changes accordingly. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally also includes steps or units that are not listed, or optionally also includes other steps or units inherent to these processes, methods, products or devices.

[0079] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0080] like Figure 1 As shown, this embodiment provides an embodiment of an automatic control method of an ecological cabin. In this embodiment, the ecological cabin includes a hollow transparent column covered by an air circulation component and an oxygenation component in sequence from top to bottom, a substrate laid on the oxygenation component, and healthy plants located in the hollow transparent column and planted on the substrate.

[0081] Preferably, the eco-capsule is a prior art, and the eco-capsule is fixed between a first structural layer and a second structural layer at different heights, such as a floor and a ceiling, and the eco-capsule comprises:

[0082] The oxygen-enriching component includes a planting trough fixedly mounted on the floor, healthy plants planted on the planting trough, and a transparent enclosure fixedly mounted on the edge of the planting trough, wherein the transparent enclosure encloses the above-mentioned hollow transparent column.

[0083] The air circulation component includes a shell covering the top end of a hollow transparent column and a first air circulation component fixedly installed in the shell. The shell is fixedly connected to the transparent enclosure to form an air duct in the transparent enclosure. The first air inlet end of the first air circulation component passes through the shell and is connected to the air duct. The first air outlet end of the first air circulation component passes through the shell and is connected to the indoor space. The first air circulation component guides external air to pass through the air inlet, the air duct, the first air inlet end, and the first air outlet end in sequence to guide external air and oxygen produced by plants to the indoor space.

[0084] Preferably, the air circulation component also includes a second air circulation component fixedly installed in the shell, the second air inlet end of the second air circulation component passes through the shell and is connected to the indoor space, the second air outlet end of the second air circulation component passes through the shell and is connected to the outdoors, and the second air circulation component guides the air in the indoor space through the second air inlet end and the second air outlet end in sequence to guide the air in the indoor space to the outdoors.

[0085] Preferably, the oxygen enrichment component also includes a drip irrigation pipe fixedly installed in the planting trough, one end of the drip irrigation pipe is connected to an external water source, and the other end of the drip irrigation pipe is closed. At least one water outlet is opened on the side wall of the drip irrigation pipe, and a solenoid valve for conducting or blocking the external water source is fixedly installed in the drip irrigation pipe. The solenoid valve is located between the water outlet and the external water source, and the solenoid valve is opened or closed according to external instructions to conduct the external water source to the water outlet or block the external water source.

[0086] It is worth noting that the structure of the above-mentioned eco-cabin is already existing technology. For details, please refer to the patent "An air circulation device based on curtain wall", application number "202322289519.3". This embodiment does not improve the structure of the eco-cabin, but is a conventional application of the eco-cabin structure.

[0087] Specifically, the automatic control method includes the following steps:

[0088] Step S1, acquiring a plurality of visual images of a healthy plant from at least two perspectives based on a preset time period.

[0089] Preferably, a shooting end can be set based on a transparent enclosure, and a shooting end can be set on the air circulation component to obtain a visual image of healthy plants from the top; if the number of transparent enclosures is four, then there are a total of five shooting ends including the shooting end on the top.

[0090] Step S2, obtaining the boundary coordinates of each visual image based on a boundary extraction algorithm.

[0091] Preferably, the coordinates are coordinates based on image pixel positions, and the same applies below.

[0092] Step S3, packing all boundary coordinates of a visual image into a coordinate data set based on the same viewing angle.

[0093] Step S4, training and learning all coordinate data sets through an extreme learning algorithm, and obtaining at least one predicted coordinate data set based on a perspective.

[0094] Step S5, obtaining the enclosed areas of all coordinate data sets and the predicted enclosed areas of all predicted coordinate data sets.

[0095] Step S6, obtaining a ratio value of the predicted enclosed area to the enclosed area based on the same viewing angle.

[0096] Step S7, determining whether the ratio value of each viewing angle is less than or equal to a preset area ratio, and defining the viewing angle whose ratio value is less than or equal to the preset area ratio as the focus viewing angle.

[0097] Preferably, the preset area ratio may be set to 90% to 95% to prevent the plants from being overly water-deficient.

[0098] Step S8, determining whether the number of all the focused viewing angles is greater than or equal to a preset number threshold, if the number of all the focused viewing angles is greater than or equal to the preset number threshold, executing step S9.

[0099] Step S9, start the air circulation component and the oxygenation component.

[0100] Preferably, the oxygenation component should not be opened for too long and can be closed after the substrate is completely infiltrated. The time required for complete infiltration of the substrate at a fixed flow rate is usually fixed.

[0101] Furthermore, step S2, based on a boundary extraction algorithm, respectively obtains the boundary coordinates of each visual image, including:

[0102] Step S21, binarizing the current visual image to obtain a black and white visual image.

[0103] Step S22, defining grids with the same resolution according to the resolution of the visual image to divide the black and white visual image.

[0104] Step S23, respectively obtain the RGB color value of each grid.

[0105] Step S24, assigning a value of 1 to the grid whose RGB color value is 0, 0, 0, and assigning a value of 0 to the grid whose RGB color value is 255, 255, 255.

[0106] Step S25, defining each grid and eight adjacent grids as a 3×3 window.

[0107] Step S26, traverse all grids through the 3×3 window with one grid as a step.

[0108] Step S27, based on all traversal results, delete the grids with all values ​​assigned to them as 1 and the grids with all values ​​assigned to them as 0 in the 3×3 window.

[0109] Step S28, obtaining the retained grid and defining it as a boundary.

[0110] Step S29, obtaining the coordinates of the boundary based on the pixel coordinates of the current visual image and defining them as boundary coordinates.

[0111] Preferably, the grid defined according to the resolution will not split the pixels again to facilitate calculation, so the coordinate values ​​of the pixel coordinates and the boundary coordinates at the same position are the same.

[0112] Further, step S4, training and learning all coordinate data sets through an extreme learning algorithm, and obtaining at least one predicted coordinate data set based on a perspective, including:

[0113] Step S10, packing all pixel color values ​​of a visual image into a color value data set.

[0114] Step S20, normalizing all color value data sets to obtain normalized data sets.

[0115] Preferably, this embodiment prefers the normalization method of zero-mean normalization (Z-score normalization), which gives the mean and standard deviation of the original data to standardize the data, and the processed data conforms to the standard normal distribution, that is, the mean is 0 and the standard deviation is 1. For the normalization method, this embodiment can also use batch normalization. Compared with simple normalization, in the previous neural network training, only the input layer data is normalized, but not normalized in the middle layer. Although the data set of the input node is normalized, the data distribution of the input data after matrix multiplication is likely to change greatly, and as the number of hidden layer network layers continues to deepen, the change in data distribution will become greater and greater. Therefore, the normalization processing performed by batch normalization in the middle layer of the neural network makes the training effect better.

[0116] Step S30, dividing the normalized data set into a training set and a validation set according to a preset ratio.

[0117] Preferably, the preset ratio is usually 80%:20% to divide the image data into a training set and a validation set, that is, 80% of the data is the training set and 20% of the data is the validation set.

[0118] Step S40, defining an extreme learning model according to the data dimension of the training set.

[0119] Preferably, the extreme learning model is a feedforward neural network that can be used to train a single hidden layer. The extreme learning machine is different from the traditional single hidden layer feedforward neural network training algorithm. The extreme learning machine randomly selects the input layer weights and hidden layer biases, and the output layer weights are calculated and analyzed based on the Moore-Penrose (MP) generalized inverse matrix theory by minimizing the loss function composed of the training error term and the regularization term of the output layer weight norm. Even if the extreme learning machine randomly generates hidden layer nodes, the extreme learning machine still maintains the general approximation ability of a single hidden layer feedforward neural network.

[0120] Step S50, training and learning the extreme learning model through the training set to obtain a prediction model.

[0121] Step S60: output the verification set to the prediction model, and obtain at least one prediction coordinate data set based on a viewing angle.

[0122] Furthermore, step S50, training and learning the extreme learning model through the training set to obtain a prediction model, includes:

[0123] Step S541, define the training set as , the number of training sets is .

[0124] in, , For the The coordinate values ​​of the normalized data set, for of A collection of n-dimensional vectors; , For the The color values ​​of the normalized dataset, for of A collection of dimensional vectors, with a subscript is the transposed matrix.

[0125] Step S542, define the extreme learning model according to formula (1):

[0126] (1).

[0127] in, , is the first connection weight between the hidden layer and the output layer of the extreme learning model; is the number of nodes in the hidden layer; is the output value of the hidden layer, ; ; is the activation function; is the input layer and the hidden layer of the extreme learning model The second connection weight of the nodes; The hidden layer The threshold of nodes.

[0128] Preferably, It can be set to activation functions such as Sigmoid function and Gaussian function.

[0129] Preferably, if the Sigmoid function is selected, then It can be expressed as:

[0130] , here .

[0131] It should be noted that the above The formula is only used to explain the principle of the Sigmoid function, and its symbolic meaning is not interoperable with other parts of the embodiment.

[0132] Step S543: randomly generate the second connection weight and threshold value through a nonlinear mapping function in the feature space based on the extreme learning model.

[0133] Step S544, obtaining the output value of the hidden layer through the randomly generated second connection weight and threshold calculation.

[0134] Step S545, according to formula (2), the optimal solution of the first connection weight is obtained by minimizing the approximate square error:

[0135] (2).

[0136] in, is the output matrix of the hidden layer; is the target matrix of the training samples; is the optimal solution; The output matrix The MP generalized inverse matrix, , The dimension is The set of weight vectors .

[0137] Step S546, obtaining the optimal solution and the second connection weight and threshold corresponding to the optimal solution and substituting them into the extreme learning model to obtain a prediction model.

[0138] Preferably, the Moore-Penrose generalized inverse matrix can be calculated by singular value decomposition .

[0139] It can be understood that the training of a single hidden layer feedforward neural network by an extreme learning machine is divided into two main stages:

[0140] Random feature maps:

[0141] The hidden layer parameters are randomly initialized, and then some nonlinear mapping is used as the activation function to map the input data to a new feature space (called the extreme learning machine feature space). In simple terms, the weights and biases on the hidden layer nodes of the extreme learning machine are randomly generated. The random feature mapping stage is different from many existing learning algorithms, such as support vector machines that use kernel functions for feature mapping, restricted Boltzmann machines in deep neural networks, and autoencoders / autodecoders for feature learning. The nonlinear mapping function in the extreme learning machine can be any nonlinear piecewise continuous function. In the extreme learning machine, the hidden layer node parameters are randomly generated according to any continuous probability distribution and are independent of the training data.

[0142] Linear parameter solution:

[0143] After the first stage, the second connection weight and threshold are randomly generated. In the second stage, only the first connection weight needs to be solved. In order to obtain the first connection weight with good effect on the training sample set, it is necessary to ensure that its training error is minimized. The target matrix of the training samples Minimize the square error as the objective function for evaluating the training error, and then find the solution with the smallest objective function is the optimal solution.

[0144] Preferably, the eigenspace is a vector space that represents a special property of a matrix. The eigenspace is a vector space consisting of all eigenvectors of the matrix. For example, for an n×n matrix A, if there exists a scalar λ and a non-zero vector x such that Ax=λx, then x is the eigenvector of A, and the vector space where the vector x is located is the eigenspace of A.

[0145] It should be noted that the meaning of the symbols in the above additional content is not interoperable with other parts of the embodiment.

[0146] Further, step S9, starting the air circulation component and the oxygenation component, includes:

[0147] Step S91, obtaining the humidity habits of healthy plants through a preset strategy.

[0148] Step S92, obtaining the air humidity in the hollow transparent column through the external detection end.

[0149] Step S93, obtaining the humidity difference between the air humidity and the humidity habit, if the humidity difference is greater than zero, executing step S94; if the humidity difference is less than zero, executing step S95.

[0150] Step S94: increasing the output power of the air circulation component at a first preset adjustment ratio.

[0151] Step S95, reducing the output power of the air circulation component at a second preset adjustment ratio.

[0152] Preferably, the first preset adjustment ratio and the second preset adjustment ratio can both be set to 5% or 10% to prevent over-adjustment in one step.

[0153] Further, in step S9, the air circulation component and the oxygenation component are turned on, and then the following steps are included:

[0154] Step S100, turning off the oxygenation component based on the preset irrigation duration.

[0155] Step S200, repeating steps S1 to S8.

[0156] Further, in step S9, the air circulation component and the oxygenation component are turned on, and then the following steps are included:

[0157] Step S1000, obtaining the opening timestamp of the air circulation component and the oxygenation component and the closing timestamp of the oxygenation component.

[0158] Step S2000, sending a start timestamp and a close timestamp to an external receiving end.

[0159] This embodiment obtains several visual images of healthy plants from at least two perspectives based on a preset time period; obtains the boundary coordinates of each visual image based on a boundary extraction algorithm; packages all boundary coordinates of a visual image into a coordinate data set based on the same perspective; trains and learns all coordinate data sets through an extreme learning algorithm, and obtains at least one predicted coordinate data set based on one perspective; obtains the enclosed area of ​​all coordinate data sets and the predicted enclosed area of ​​all predicted coordinate data sets; obtains the ratio of the predicted enclosed area to the enclosed area based on the same perspective; determines whether the ratio value of each perspective is less than or equal to the preset area ratio, and defines the perspective with a ratio value less than or equal to the preset area ratio as a focus perspective; determines whether the number of all focus perspectives is greater than or equal to a preset number threshold; if the number of all focus perspectives is greater than or equal to the preset number threshold, turns on the air circulation component and the oxygen enrichment component. The present embodiment utilizes that the yellowing, wilting, leaf shedding, overall wilting and death of plant leaves are all shrinkage processes caused by reduced water content, and its intuitive visual effect is the reduction in the visual area of ​​the plant at multiple viewing angles. The plant can exhibit this characteristic when it is initially short of water, and the visual area will continue to decrease as the degree of water shortage increases, that is, the degree of water shortage and the visual area are positively correlated, so that the present embodiment can capture this characteristic through at least two viewing angles, and there is no need to identify the plant variety, and the degree of water shortage can be judged only by the visual area. It is suitable for plants of different colors, and the oxygenation component is turned on when the visual area is reduced at multiple viewing angles to prevent the plant from being short of water for a long time or being redundantly irrigated, thereby ensuring the healthy growth of the plant. At the same time, the increased visual area during plant growth does not affect the entire process of the present embodiment. Since the visual image of the plant is repeatedly acquired at intervals of a certain period of time in the initial step, the growth characteristics will be continuously updated, and will not lead to inaccurate subsequent judgments.

[0160] like Figure 2 As shown, this embodiment provides an embodiment of an automatic control device for an ecological cabin. In this embodiment, the automatic control device is applied to the automatic control method in the above embodiment.

[0161] Specifically, the automatic control device includes functional modules electrically connected in sequence: a visual image acquisition module 1, a boundary coordinate acquisition module 2, a coordinate data set packaging module 3, a predicted coordinate data set acquisition module 4, an enclosed area acquisition and prediction module 5, an enclosed area difference acquisition module 6, an enclosed area difference judgment module 7, a focus viewing angle number judgment module 8, and an air circulation component and oxygen enrichment component activation module 9.

[0162] Among them, the visual image acquisition module 1 is used to acquire several visual images of healthy plants from at least two perspectives based on a preset time period; the boundary coordinate acquisition module 2 is used to acquire the boundary coordinates of each visual image based on a boundary extraction algorithm; the coordinate data set packaging module 3 is used to package all boundary coordinates of a visual image into a coordinate data set based on the same perspective; the predicted coordinate data set acquisition module 4 is used to train and learn all coordinate data sets through an extreme learning algorithm, and obtain at least one predicted coordinate data set based on one perspective; the enclosed area acquisition and prediction module 5 is used to acquire the enclosed area of ​​all coordinate data sets and the predicted enclosed area of ​​all predicted coordinate data sets; the enclosed area difference acquisition module 6 is used to acquire the ratio of the predicted enclosed area to the enclosed area based on the same perspective; the enclosed area difference judgment module 7 is used to judge whether the ratio value of each perspective is less than or equal to the preset area ratio, and define the perspective whose ratio value is less than or equal to the preset area ratio as the perspective of interest; the perspective number judgment module 8 is used to judge whether the number of all perspectives of interest is greater than or equal to the preset number threshold; the air circulation component and the oxygenation component activation module 9 is used to activate the air circulation component and the oxygenation component if the number of all perspectives of interest is greater than or equal to the preset number threshold.

[0163] Furthermore, the boundary coordinate acquisition module 2 specifically includes a first boundary coordinate acquisition submodule, a second boundary coordinate acquisition submodule, a third boundary coordinate acquisition submodule, a fourth boundary coordinate acquisition submodule, a fifth boundary coordinate acquisition submodule, a sixth boundary coordinate acquisition submodule, a seventh boundary coordinate acquisition submodule, an eighth boundary coordinate acquisition submodule, and a ninth boundary coordinate acquisition submodule, which are electrically connected in sequence; the first boundary coordinate acquisition submodule is electrically connected to the visual image acquisition module 1, and the ninth boundary coordinate acquisition submodule is electrically connected to the coordinate data set packaging module 3.

[0164] Among them, the first boundary coordinate acquisition submodule is used to binarize the current visual image to obtain a black and white visual image; the second boundary coordinate acquisition submodule is used to define grids of the same resolution according to the resolution of the visual image to divide the black and white visual image; the third boundary coordinate acquisition submodule is used to respectively obtain the RGB color value of each grid; the fourth boundary coordinate acquisition submodule is used to assign 1 to the grids with RGB color values ​​of 0, 0, 0, and assign 0 to the grids with RGB color values ​​of 255, 255, 255; the fifth boundary coordinate acquisition submodule is used to define each grid and the eight adjacent grids as a 3×3 window; the sixth boundary coordinate acquisition submodule is used to traverse all grids through the 3×3 window with one grid as a step on all grids; the seventh boundary coordinate acquisition submodule is used to delete the grids with all values ​​assigned to 1 and the grids with all values ​​assigned to 0 in the 3×3 window based on all traversal results; the eighth boundary coordinate acquisition submodule is used to obtain the retained grids and define them as boundaries; the ninth boundary coordinate acquisition submodule is used to obtain the coordinates of the boundary based on the pixel coordinates of the current visual image and define them as boundary coordinates.

[0165] Furthermore, the predicted coordinate dataset acquisition module 4 specifically includes a first predicted coordinate dataset acquisition submodule, a second predicted coordinate dataset acquisition submodule, a third predicted coordinate dataset acquisition submodule, a fourth predicted coordinate dataset acquisition submodule, a fifth predicted coordinate dataset acquisition submodule, and a sixth predicted coordinate dataset acquisition submodule, which are electrically connected in sequence; the first predicted coordinate dataset acquisition submodule is electrically connected to the coordinate dataset packaging module 3, and the sixth predicted coordinate dataset acquisition submodule is electrically connected to the enclosed area acquisition and prediction module 5.

[0166] Among them, the first prediction coordinate data set acquisition submodule is used to package all pixel color values ​​of a visual image into a color value data set; the second prediction coordinate data set acquisition submodule is used to normalize all color value data sets to obtain a normalized data set; the third prediction coordinate data set acquisition submodule is used to divide the normalized data set into a training set and a verification set according to a preset ratio; the fourth prediction coordinate data set acquisition submodule is used to define an extreme learning model according to the data dimension of the training set; the fifth prediction coordinate data set acquisition submodule is used to train and learn the extreme learning model through the training set to obtain a prediction model; the sixth prediction coordinate data set acquisition submodule is used to output the verification set to the prediction model, and obtain at least one prediction coordinate data set based on a perspective.

[0167] Furthermore, the fifth predicted coordinate dataset acquisition submodule specifically includes a first predicted coordinate dataset acquisition unit, a second predicted coordinate dataset acquisition unit, a third predicted coordinate dataset acquisition unit, a fourth predicted coordinate dataset acquisition unit, a fifth predicted coordinate dataset acquisition unit, and a sixth predicted coordinate dataset acquisition unit, which are electrically connected in sequence; the first predicted coordinate dataset acquisition unit is electrically connected to the fourth predicted coordinate dataset acquisition submodule, and the sixth predicted coordinate dataset acquisition unit is electrically connected to the sixth predicted coordinate dataset acquisition submodule.

[0168] The first prediction coordinate data set acquisition unit is used to define the training set as , the number of training sets is .

[0169] in, , For the The coordinate values ​​of the normalized data set, for of A collection of n-dimensional vectors; , For the The color values ​​of the normalized dataset, for of A collection of dimensional vectors, with a subscript is the transposed matrix.

[0170] The second prediction coordinate data set acquisition unit is used to define the extreme learning model according to formula (1):

[0171] (1).

[0172] in, , is the first connection weight between the hidden layer and the output layer of the extreme learning model; is the number of nodes in the hidden layer; is the output value of the hidden layer, ; ; is the activation function; is the input layer and the hidden layer of the extreme learning model The second connection weight of the nodes; The hidden layer The threshold of nodes.

[0173] The third prediction coordinate data set acquisition unit is used to randomly generate the second connection weight and threshold value through a nonlinear mapping function in the feature space based on the extreme learning model.

[0174] The fourth predicted coordinate data set acquisition unit is used to obtain the output value of the hidden layer through the randomly generated second connection weight and threshold calculation.

[0175] The fifth prediction coordinate data set acquisition unit is used to solve the optimal solution of the first connection weight by minimizing the approximate square error according to formula (2):

[0176] (2).

[0177] in, is the output matrix of the hidden layer; is the target matrix of the training samples; is the optimal solution; The output matrix The MP generalized inverse matrix, , The dimension is The set of weight vectors .

[0178] The sixth prediction coordinate data set acquisition unit is used to acquire the optimal solution and the second connection weight and threshold corresponding to the optimal solution and substitute them into the extreme learning model to obtain the prediction model.

[0179] Furthermore, the air circulation component and oxygenation component opening module 9 specifically includes a first air circulation component and oxygenation component opening submodule, a second air circulation component and oxygenation component opening submodule, a third air circulation component and oxygenation component opening submodule, a fourth air circulation component and oxygenation component opening submodule, and a fifth air circulation component and oxygenation component opening submodule, which are electrically connected in sequence; the first air circulation component and oxygenation component opening submodule is electrically connected to the focus viewing angle number judgment module 8.

[0180] Among them, the first air circulation component and oxygenation component opening submodule is used to obtain the humidity habits of healthy plants through a preset strategy; the second air circulation component and oxygenation component opening submodule is used to obtain the air humidity in the hollow transparent column through an external detection end; the third air circulation component and oxygenation component opening submodule is used to obtain the humidity difference between the air humidity and the humidity habits; the fourth air circulation component and oxygenation component opening submodule is used to increase the output power of the air circulation component at a first preset adjustment ratio if the humidity difference is greater than zero; the fifth air circulation component and oxygenation component opening submodule is used to reduce the output power of the air circulation component at a second preset adjustment ratio if the humidity difference is less than zero.

[0181] Furthermore, the automatic control device also includes an oxygenation component closing module and an instruction repeating module which are electrically connected in sequence; the oxygenation component closing module is electrically connected to the air circulation component and the oxygenation component opening module 9 .

[0182] Among them, the oxygenation component closing module is used to close the oxygenation component based on the preset irrigation time; the instruction repetition module is used to repeatedly execute the visual image acquisition module 1 to the focus angle number judgment module 8.

[0183] Furthermore, the automatic control device also includes a timestamp acquisition module and a timestamp sending module which are electrically connected in sequence; the timestamp acquisition module is electrically connected to the oxygenation component start module 9.

[0184] Among them, the timestamp acquisition module is used to obtain the opening timestamp of the air circulation component and the oxygenation component and the closing timestamp of the oxygenation component; the timestamp sending module is used to send the opening timestamp and the closing timestamp to the external receiving end.

[0185] It should be noted that this embodiment is a functional module embodiment based on the above method embodiment. The optimization, expansion, limitation, example, and principle description of this embodiment can be referred to the above embodiment, and this embodiment will not be repeated.

[0186] This embodiment obtains several visual images of healthy plants from at least two perspectives based on a preset time period; obtains the boundary coordinates of each visual image based on a boundary extraction algorithm; packages all boundary coordinates of a visual image into a coordinate data set based on the same perspective; trains and learns all coordinate data sets through an extreme learning algorithm, and obtains at least one predicted coordinate data set based on one perspective; obtains the enclosed area of ​​all coordinate data sets and the predicted enclosed area of ​​all predicted coordinate data sets; obtains the ratio of the predicted enclosed area to the enclosed area based on the same perspective; determines whether the ratio value of each perspective is less than or equal to the preset area ratio, and defines the perspective with a ratio value less than or equal to the preset area ratio as a focus perspective; determines whether the number of all focus perspectives is greater than or equal to a preset number threshold; if the number of all focus perspectives is greater than or equal to the preset number threshold, turns on the air circulation component and the oxygen enrichment component. The present embodiment utilizes that the yellowing, wilting, leaf shedding, overall wilting and death of plant leaves are all shrinkage processes caused by reduced water content, and its intuitive visual effect is the reduction in the visual area of ​​the plant at multiple viewing angles. The plant can exhibit this characteristic when it is initially short of water, and the visual area will continue to decrease as the degree of water shortage increases, that is, the degree of water shortage and the visual area are positively correlated, so that the present embodiment can capture this characteristic through at least two viewing angles, and there is no need to identify the plant variety, and the degree of water shortage can be judged only by the visual area. It is suitable for plants of different colors, and the oxygenation component is turned on when the visual area is reduced at multiple viewing angles to prevent the plant from being short of water for a long time or being redundantly irrigated, thereby ensuring the healthy growth of the plant. At the same time, the increased visual area during plant growth does not affect the entire process of the present embodiment. Since the visual image of the plant is repeatedly acquired at intervals of a certain period of time in the initial step, the growth characteristics will be continuously updated, and will not lead to inaccurate subsequent judgments.

[0187] Figure 3 Schematic diagram of the structure of an electronic device according to an embodiment of the present application. Figure 3 As shown, the electronic device 10 includes a processor 101 and a memory 102 coupled to the processor 101 .

[0188] The memory 102 stores program instructions for implementing the automatic control method of the eco-cabin in any of the above embodiments.

[0189] The processor 101 is used to execute program instructions stored in the memory 102 to perform automatic regulation of the eco-cabin.

[0190] The processor 101 may also be referred to as a CPU (Central Processing Unit). The processor 101 may be an integrated circuit chip having a signal processing capability. The processor 101 may also be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0191] Further, Figure 4 This is a schematic diagram of the structure of a storage medium according to an embodiment of the present application. Figure 4 The storage medium 11 of the embodiment of the present application stores program instructions 111 that can implement all the above methods, wherein the program instructions 111 can be stored in the above storage medium in the form of a software product, including several instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) or a processor to execute all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes, or terminal devices such as computers, servers, mobile phones, tablets, etc.

[0192] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0193] In addition, each functional unit in each embodiment of the present application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above integrated unit can be implemented in the form of hardware or in the form of software functional units. The above is only an implementation method of the present application, and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the specification and drawings of this application, or directly or indirectly used in other related technical fields, is also included in the patent protection scope of the present application.

Claims

1. An automatic control method for an ecological cabin, the ecological cabin comprising a hollow transparent column covered by an air circulation component and an oxygenation component in sequence, a substrate laid on the oxygenation component, and healthy plants located in the hollow transparent column and planted on the substrate, characterized in that: The automatic control method comprises: Step S1, acquiring a plurality of visual images of the healthy plant from at least two perspectives based on a preset time period; Step S2, obtaining the boundary coordinates of each visual image based on a boundary extraction algorithm; Step S3, packing all boundary coordinates of a visual image into a coordinate data set based on the same viewing angle; Step S4, training and learning all coordinate data sets through an extreme learning algorithm, and obtaining at least one predicted coordinate data set based on one perspective; Step S5, obtaining the enclosed area of ​​all coordinate data sets and the predicted enclosed area of ​​all predicted coordinate data sets; Step S6, obtaining a ratio value of the predicted enclosed area to the enclosed area based on the same viewing angle; Step S7, determining whether the ratio value of each viewing angle is less than or equal to a preset area ratio, and defining the viewing angle whose ratio value is less than or equal to the preset area ratio as the focus viewing angle; Step S8, determining whether the number of all concerned viewing angles is greater than or equal to a preset number threshold, if the number of all concerned viewing angles is greater than or equal to the preset number threshold, executing step S9; Step S9, turning on the air circulation component and the oxygenation component; Step S4, training and learning all coordinate data sets through an extreme learning algorithm, and obtaining at least one predicted coordinate data set based on a perspective, including: Step S10, packing all pixel color values ​​of a visual image into a color value data set; Step S20, normalizing all color value data sets to obtain normalized data sets; Step S30, dividing the normalized data set into a training set and a validation set according to a preset ratio; Step S40, defining an extreme learning model according to the data dimension of the training set; Step S50, training and learning the extreme learning model through the training set to obtain a prediction model; Step S60, outputting the verification set to the prediction model, and obtaining at least one prediction coordinate data set based on a viewing angle; Step S9, starting the air circulation component and the oxygenation component, includes: Step S91, obtaining the humidity habits of the healthy plants through a preset strategy; Step S92, obtaining the air humidity in the hollow transparent column through an external detection terminal; Step S93, obtaining the humidity difference between the air humidity and the humidity habit, if the humidity difference is greater than zero, executing step S94; if the humidity difference is less than zero, executing step S95; Step S94, increasing the output power of the air circulation component at a first preset adjustment ratio; Step S95, reducing the output power of the air circulation component at a second preset adjustment ratio.

2. The automatic control method according to claim 1, characterized in that: Step S2, obtaining the boundary coordinates of each visual image based on a boundary extraction algorithm, including: Step S21, binarizing the current visual image to obtain a black and white visual image; Step S22, defining grids with the same resolution according to the resolution of the visual image to divide the black and white visual image; Step S23, respectively obtaining the RGB color value of each grid; Step S24, assigning a value of 1 to a grid whose RGB color value is 0, 0, 0, and assigning a value of 0 to a grid whose RGB color value is 255, 255, 255; Step S25, defining each grid and eight adjacent grids as a 3×3 window; Step S26, traversing all grids through the 3×3 window with one grid as one step; Step S27, based on all traversal results, delete the grids whose values ​​are all 1 and the grids whose values ​​are all 0 in the 3×3 window; Step S28, obtaining the retained grid and defining it as a boundary; Step S29, obtaining the coordinates of the boundary based on the pixel coordinates of the current visual image and defining them as the boundary coordinates.

3. The automatic control method according to claim 1, characterized in that: Step S50, training and learning the extreme learning model through the training set to obtain a prediction model, includes: Step S541, define the training set as , the number of training sets is ; in, , For the The coordinate values ​​of the normalized data set, for of A collection of n-dimensional vectors; , For the The color values ​​of the normalized dataset, for of A collection of dimensional vectors, with a subscript is the transposed matrix; Step S542, defining the extreme learning model according to formula (1): （1）； in, , is the first connection weight between the hidden layer and the output layer of the extreme learning model; is the number of nodes in the hidden layer; is the output value of the hidden layer, ; ; is the activation function; is the input layer of the extreme learning model and the hidden layer The second connection weight of the nodes; is the hidden layer The threshold of nodes; Step S543, randomly generating the second connection weight and the threshold value by a nonlinear mapping function in a feature space based on the extreme learning model; Step S544, obtaining the output value of the hidden layer by calculating the randomly generated second connection weight and the threshold; Step S545, according to formula (2), the optimal solution of the first connection weight is solved by minimizing the approximate square error: （2）； in, is the output matrix of the hidden layer; is the target matrix of the training sample; is the optimal solution; The output matrix The MP generalized inverse matrix, , The dimension is The set of weight vectors of ; Step S546, obtaining the optimal solution and the second connection weight and threshold corresponding to the optimal solution and substituting them into the extreme learning model to obtain the prediction model.

4. The automatic control method according to claim 1, characterized in that: Step S9, turning on the air circulation component and the oxygenation component, and then comprising: Step S100, closing the oxygenation component based on a preset irrigation duration; Step S200, repeating steps S1 to S8.

5. The automatic control method according to claim 4, characterized in that: Step S9, turning on the air circulation component and the oxygenation component, and then comprising: Step S1000, obtaining the opening timestamps of the air circulation component and the oxygenation component and the closing timestamp of the oxygenation component; Step S2000: sending the opening timestamp and the closing timestamp to an external receiving end.

6. An automatic control device for an eco-capsule, the automatic control device being applied to the automatic control method for an eco-capsule as claimed in any one of claims 1 to 5, characterized in that: The automatic control device comprises: A visual image acquisition module, used for acquiring a plurality of visual images of the healthy plant from at least two viewing angles based on a preset time period; A boundary coordinate acquisition module, used to respectively acquire the boundary coordinates of each visual image based on a boundary extraction algorithm; A coordinate data set packaging module, used to package all boundary coordinates of a visual image into a coordinate data set based on the same viewing angle; A predicted coordinate data set acquisition module, used to train and learn all coordinate data sets through an extreme learning algorithm, and obtain at least one predicted coordinate data set based on a perspective; The enclosed area acquisition and prediction module is used to obtain the enclosed areas of all coordinate data sets and the predicted enclosed areas of all predicted coordinate data sets; An enclosed area difference acquisition module, used for acquiring a ratio value between the predicted enclosed area and the enclosed area based on the same viewing angle; The enclosed area difference judgment module is used to judge whether the ratio value of each viewing angle is less than or equal to the preset area ratio, and define the viewing angle whose ratio value is less than or equal to the preset area ratio as the focus viewing angle; A module for determining the number of viewing angles of interest, used to determine whether the number of all viewing angles of interest is greater than or equal to a preset number threshold; The air circulation component and the oxygenation component activation module is used to activate the air circulation component and the oxygenation component if the number of all concerned viewing angles is greater than or equal to a preset number threshold.

7. An electronic device, characterized in that: It includes a processor and a memory coupled to the processor, wherein the memory stores program instructions that can be executed by the processor; when the processor executes the program instructions stored in the memory, the automatic control method of the eco-cabin as described in any one of claims 1 to 5 is implemented.

8. A storage medium, characterized in that: The storage medium stores program instructions, and when the program instructions are executed by the processor, the automatic control method of the eco-cabin as described in any one of claims 1 to 5 can be implemented.

Images