Dish washing machine based on AI technology and automatic control method thereof

Abstract

The invention is suitable for the technical field of dish-washing machine control, and provides a dish-washing machine based on the AI technology and an automatic control method of the dish-washing machine based on the AI technology. The system comprises an information acquisition module, a model construction module, a model training module, a model evaluation module, a parameter determination module, an application control module, a wireless communication module, a memory, an alarm, a processing center and an intelligent mobile terminal. The information acquisition module, the model construction module, the model training module, the model evaluation module, the parameter determination module, the application control module, the wireless communication module, the memory and the alarm are respectively connected with the processing center; the intelligent mobile terminal is in wireless network connection with the wireless communication module in the range of a wireless network or the Internet. The invention further provides the dish washing machine based on the AI technology. Different cleaning processes can be adopted according to different tableware, and energy conservation and environmental protection are achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of dishwasher control, and specifically to a dishwasher based on AI technology and its automatic control method in the field of artificial intelligence. Background Art

[0002] With the application of Internet of Things technology and artificial intelligence technology in many industries, the technology of dishwashers has been continuously innovated and upgraded. As an important sub-industry in smart home, intelligent dishwashing has attracted more and more attention from consumers. Consumers have put forward new requirements for the intelligence of dishwashers. The 5G era and Internet technology have accelerated the iteration of intelligent dishwashers, making consumers have new demands for the intelligence, high-endization and adaptability to various usage scenarios of dishwashers. For intelligent dishwashers, in addition to being able to wash dishes to improve the cleaning effect, it is also necessary to improve the sterilization ability, while paying attention to energy conservation and environmental protection. However, the existing dishwashers only have different cleaning grades and require manual selection of the cleaning grade, and cannot automatically identify according to the type of substances to be washed and automatically select the corresponding water power and heat for cleaning, which cannot ensure energy conservation and is very water and electricity consuming. Summary of the Invention

[0003] In order to solve the deficiencies in the prior art, the purpose of the present invention is to provide a dishwasher based on AI technology and its automatic control method. By setting up various functional modules such as an information acquisition module, a model construction module, a model training module, a model evaluation module, a parameter determination module, and an application control module, it can prevent problems in advance by collecting abnormal phenomena during daily dishwashing, preset control parameters, and perform automatic identification and control to achieve the purpose of energy conservation and environmental protection. Incorporating AI artificial intelligence and Internet of Things technology, it has functions such as Wi-Fi connection, remote control, and intelligent adjustment, which not only improves the user experience satisfaction but also reduces the application cost.

[0004] In order to achieve the above purpose, the technical solution adopted by the present invention is:

[0005] An automatic control method for a dishwasher based on AI technology, which is applied to a dishwasher control system based on AI technology. The system includes an information acquisition module, a model construction module, a model training module, a model evaluation module, a parameter determination module, an application control module, a wireless communication module, a memory, an alarm, a processing center, and an intelligent mobile terminal; the information acquisition module, the model construction module, the model training module, the model evaluation module, the parameter determination module, the application control module, the wireless communication module, the memory, and the alarm are respectively connected to the processing center; the intelligent mobile terminal includes a smart phone, a tablet computer, and a smart remote control, and is wirelessly connected to the wireless communication module within the range of a wireless network or the Internet.

[0006] The wireless communication module is provided with a wireless network unit, which is responsible for the transceiver of wireless signals and automatically forms a network connection with the intelligent mobile terminal within an effective network range;

[0007] The alarm compares the actual evaluation score of the model with the model evaluation score standard stored in the memory. If it does not meet the standard, it will automatically give an audible alarm and notify to continue training; and compares the quality information of the dishwasher with the dishwasher washing quality standard stored in the memory. If it does not meet the standard, it will automatically give an audible alarm and notify to adjust the parameters and rework; and compares the quality information of the dishwasher with the dishwasher washing quality standard stored in the memory. If it does not meet the standard, it will automatically give an audible alarm and notify to rework or repair again;

[0008] The memory is responsible for storing the information of the information acquisition module, model construction module, model training module, model evaluation module, parameter determination module, application control module, wireless communication module, and alarm, as well as storing the model evaluation score standard and the dishwasher washing quality standard;

[0009] The processing center is responsible for the information transfer of each functional module, alarm, and memory, and is the hub center of the system. It compares the actual evaluation score of the model with the model evaluation score standard stored in the memory: if it meets the standard, it is the predetermined dishwasher control parameter; if it does not meet the standard, it is transferred to the alarm and notifies to continue training; and compares the quality information of the dishwasher with the dishwasher washing quality standard stored in the memory: if it meets the standard, it is set as the formal dishwashing control parameter; if it does not meet the standard, it is transferred to the alarm and notifies to adjust the parameters and rework; and compares the quality information of the dishwasher with the dishwasher washing quality standard stored in the memory: if it meets the standard, it notifies that the dishwashing is completed; if it does not meet the standard, it is transferred to the alarm and notifies to rework or repair again;

[0010] The information acquisition module includes a data acquisition unit, a cleaning data unit, an enhancement data unit, an integration data unit, a conversion data unit, a filtering and denoising unit, a grayscale conversion unit, and a feature extraction unit, which is responsible for acquiring the normal and abnormal historical image data produced by the dishwasher, preprocessing it, and transferring it to the model construction module;

[0011] The model construction module includes a network layer unit, a network parameter unit, a hierarchical optimization unit, and a data division unit, which is responsible for determining the model architecture, designing the network layer structure, adding auxiliary layers, and defining model parameters according to the extracted feature information to construct the model, and transferring it to the model training module;

[0012] The model training module includes an input filling unit, a convolutional input unit, a pooling conversion unit, a fully connected layer unit, a normalization output unit, an output conversion unit, and a backpropagation unit, which are responsible for training the model according to the collected data, adjusting the model parameters to optimize the model performance to predetermined dishwasher control parameters, and transmitting them to the model evaluation module;

[0013] The model evaluation module includes a classification marking unit, a learning and training unit, and a model evaluation unit, which are responsible for validating and evaluating the model according to the trained model, adjusting and optimizing the model according to the verification results, and transmitting them to the parameter determination module;

[0014] The parameter determination module includes a cleaning power consumption unit, a cleaning water consumption unit, a trial debugging unit, and an anomaly recognition unit, which are responsible for conducting cleaning tests on different tableware according to the dishwasher control parameters predicted by the trained model to obtain the optimal dishwasher control parameters, and transmitting them to the application control module;

[0015] The application control module includes a category acquisition unit, a slag removal and soaking unit, a spray rinsing unit, a disinfection and drying unit, an appearance detection unit, and a hygiene detection unit, which are responsible for controlling the dishwasher according to the set dishwasher control parameters and program instructions and conducting various quality inspections to ensure that the dishwasher meets the quality requirements after automatic dishwashing.

[0016] An automatic control method for a dishwasher based on AI technology provided by the invention includes the following steps:

[0017] S10. Before application, the information acquisition module acquires the normal and abnormal historical image data produced by the dishwasher and performs preprocessing for subsequent model construction, and transmits them to the model construction module;

[0018] S20. The model construction module constructs a model by determining the model architecture, designing the network hierarchy structure, adding auxiliary layers, and defining model parameters according to the extracted feature information for subsequent model training and verification, and transmits them to the model training module;

[0019] S30. The model training module trains the model according to the collected data, adjusts the model parameters to optimize the model performance to predetermined dishwasher control parameters, ensures the quality stability of the dishwasher operation, and transmits them to the model evaluation module;

[0020] S40. The model evaluation module validates and evaluates the model according to the trained model, and adjusts and optimizes the model according to the verification results to improve the performance and accuracy of the model, and transmits them to the parameter determination module;

[0021] S50. The parameter determination module conducts washing tests on different tableware according to the dishwashing control parameters predicted by the trained model to obtain the optimal dishwasher control parameters, so as to ensure the subsequent dishwashing quality and transmit them to the application control module;

[0022] S60. The application control module conducts dishwashing control on the dishwasher according to the set dishwashing control parameters and program instructions and conducts various quality inspections to ensure that the dishwasher meets the quality requirements after automatic dishwashing.

[0023] Further, the step S10 includes the following steps:

[0024] S11. The data acquisition unit obtains historical data on the dirtiness degree, quantity, type of different tableware, the cleaning effect after cleaning by a similar dishwasher, and its control parameters by connecting to the industry database, and transmits them to the cleaning data unit;

[0025] S12. The cleaning data unit cleans the collected dishwashing historical data to remove outliers, duplicate values or missing values in the data, so as to improve the quality and accuracy of the data, and transmits them to the enhanced data unit;

[0026] S13. The enhanced data unit uses data augmentation methods such as rotation, scaling, flipping, cropping, and color transformation to increase the quantity and diversity of dishwashing training data, so as to improve the generalization ability of the model, and transmits them to the integrated data unit;

[0027] S14. The integrated data unit obtains the standardized dishwashing data according to the data standardization processing formula "z = (x - μ) / σ, where z is the standardized data, x is the original data, μ is the mean of the data, and σ is the standard deviation of the data" to improve the stability of the model, and transmits them to the conversion data unit;

[0028] S15. The conversion data unit obtains the normalized dishwashing data according to the normalization calculation formula "x' = (x - min(x)) / (max(x) - min(x)), where x' is the normalized data, x is the original data, and min(x) and max(x) are the minimum and maximum values of the data respectively" to improve the model performance, and transmits them to the filtering and denoising unit;

[0029] S16. The filtering and denoising unit obtains the denoised dishwashing image data according to the Gaussian filtering method calculation formula " G(x, y) is the pixel of the two-dimensional Gaussian function, (x, y) is the pixel coordinate, and σ is the standard deviation" to facilitate grayscale image conversion, and transmits them to the grayscale conversion unit;

[0030] S17. The grayscale conversion unit obtains the grayscale dishwashing image data according to the grayscale calculation formula "f(i,j) = max(R(i,j), G(i,j), B(i,j)), where f(i,j) is the image after grayscale conversion, and R(i,j), G(i,j), and B(i,j) are the original images of the three colors" for subsequent feature extraction and transmits it to the feature extraction unit;

[0031] S18. The feature extraction unit converts the labeled data into feature vectors useful for model training and extracts the key features of the appearance cleanliness, dryness degree, and hygiene index to improve the training speed and performance of the model.

[0032] Further, step S20 includes the following steps:

[0033] S21. The network layer unit customizes and optimizes the network layer structure according to the selected convolutional neural network as the model architecture and based on the specific application scenario and requirements for subsequent defect detection and quality recognition, and transmits it to the network parameter unit;

[0034] S22. The network parameter unit adjusts the number of network layers, the size of the convolutional kernel, the stride, the padding method, and selects the loss function and optimization algorithm according to the network layer structure to ensure the performance and accuracy of the model, and transmits it to the hierarchical optimization unit;

[0035] S23. The hierarchical optimization unit adjusts the size of the input data and performs normalization processing by adding zero-padding layers and normalization layers before and after the convolutional layer respectively to improve the model training speed and stability, and transmits it to the data partitioning unit;

[0036] S24. The data partitioning unit divides the dataset with the extracted key feature vectors into a training set, a validation set, and a test set and establishes a convolutional neural network structure for subsequent model training.

[0037] Further, step S30 includes the following steps:

[0038] S31. The input padding unit according to the data padding size calculation formula

[0039] "P H = [(Ho - 1) * S H + K H - Hi] / 2, P W = [(Wo - 1) * S W + K W - Wi] / 2, P H 、P W are the padding sizes in the height / width directions respectively, Hi and Wi are the height / width of the input feature map, K H 、K WThey are the height / width of the convolution kernel, S H 、S W They are the values of the stride in the height / width directions respectively. Ho and Wo are the height and width of the output feature map respectively. "Obtain the padding data and input it, and transfer it to the convolution input unit;

[0040] S32. The convolution input unit obtains the convolution input value according to the convolution input calculation formula "z(t) = ∫x(m)y(t - m)dm, where z(t) is the output function, x(t) is the input function, y(t) is the convolution kernel function, and dm is the integral differential element of the variable m", activates the function input, and transfers it to the pooling conversion unit;

[0041] S33. The pooling conversion unit obtains the maximum pixel value after pooling according to the max pooling calculation formula "Z(i,j) = max(X[i*P S (i + 1)*P S ,j*P S (j + 1)*P S )), where Z(i,j) is a pixel value in the output feature map after pooling, i and j are the positions in the output feature map respectively, max is to find the maximum value among all pixel values in the input window, X is the input feature map, and P S is the window size of the pooling operation", enters the fully connected layer to retain important feature information, and transfers it to the fully connected layer unit;

[0042] S34. The fully connected layer unit obtains the output data of the connection layer according to the fully connected layer calculation formula "y = f(∑(wn*xn)+b), where y is the output result, f is the activation function, wn is the weight of the nth input feature, xn is the n input features, n is the dimension of the input features, and b is the bias", enters the output layer for subsequent output calculation, and transfers it to the normalized output unit;

[0043] S35. The normalized output unit obtains the output of Batch Norm according to the Batch Norm layer calculation formula "h = φ(B N (Wx + b)), where h is the output of the fully connected layer, φ is the activation function, B N is the operator for batch normalization, W is the weight parameter, x is the input of the fully connected layer, and b is the bias parameter", and transfers it to the output conversion unit;

[0044] S36. The output conversion unit obtains the size of the output value after convolution according to the output layer conversion calculation formula "N = (P - F + 2C) / S + 1, where N is the output size after convolution, P is the input size before convolution, F is the convolution kernel size, C is the number of layers of adding 0 around the image, and S is the stride size", for subsequent model analysis and training, and transfers it to the backpropagation unit;

[0045] S37. The backpropagation unit obtains the loss function value according to the loss function calculation formula "L = max(0, m + y * (f(x) - b)), where L is the loss function value, m is a hyperparameter, y is the sample label (0 or 1), f(x) is the predicted value of the model, and b is the classification boundary", and performs backpropagation to optimize the performance of the network model.

[0046] Further, step S40 includes the following steps:

[0047] S41. The classification marking unit classifies and marks the corresponding data sample categories according to the dishwashing quality anomaly categories for subsequent machine learning of the model, and transmits them to the learning and training unit;

[0048] S42. The learning and training unit determines the training model according to the gradient descent data, and inputs the data in the training set into the model for simulation training under different environmental conditions to ensure the accuracy of model recognition, and transmits it to the model evaluation unit;

[0049] S43. The model evaluation unit obtains the comprehensive evaluation score F according to the model evaluation score calculation formula "F = 2(Ac * Re) / (Ac + Re), where F is the evaluation score of the training model, Ac is the precision rate, and Re is the recall rate", and transmits it to the processing center;

[0050] S44. The processing center compares the actual evaluation score of the model with the model evaluation score standard stored in the memory: if it meets the standard, it is the predetermined dishwasher control parameter; if it does not meet the standard, it is transmitted to the alarm and notifies to continue training until it meets the standard.

[0051] Further, step S50 includes the following steps:

[0052] S51. The cleaning power consumption unit obtains the power consumption of dishwashing cleaning and drying according to the dishwashing power consumption calculation formula "E = P1 * T1 + P2 * T2, where E is the dishwashing power consumption (kWh), P1 and P2 are the powers (kW) of dishwashing cleaning and drying respectively, and T1 and T2 are the times (h) of dishwashing cleaning and drying respectively" for subsequent dishwashing power consumption calculation, and transmits it to the cleaning water consumption unit;

[0053] S52. The cleaning water consumption unit obtains the dishwashing cleaning water consumption according to the dishwashing water consumption calculation formula "W = πR 2 * υ * T1, where W is the dishwashing water consumption (m 3 ), R is the radius (m) of the dishwasher's water spray nozzle, υ is the water spray flow rate (m / s) of the dishwasher, and T1 is the dishwashing cleaning time (s)", for subsequent dishwashing water consumption calculation, and transmits it to the trial debugging unit;

[0054] S54. The trial debugging unit conducts cleaning tests on different tableware through the dishwasher according to the predetermined dishwashing control parameters, detects and obtains the quality information of the cleaning to ensure the accuracy of the dishwashing quality, and transmits it to the processing center;

[0055] S55. The processing center compares the quality information of the dishwasher with the dishwasher dishwashing quality standard stored in the memory: if it meets the standard, it is set as the formal dishwashing control parameter; if it does not meet the standard, it is transmitted to the alarm and notifies to adjust the parameters for rework.

[0056] S56. The anomaly recognition unit matches the real-time obtained operating image of the dishwasher with the corresponding image in the trained convolutional neural network model and confirms its anomaly category for subsequent improvement of the dishwashing process and parameter adjustment.

[0057] Furthermore, the step S60 includes the following steps:

[0058] S61. The category acquisition unit obtains the material and oil stain degree of the tableware to be cleaned through a high-definition camera, combines the washing requirements with the model to match the corresponding washing program, which can save energy and be environmentally friendly on the premise of ensuring clean washing, and transmits it to the slag removal and soaking unit;

[0059] S62. The slag removal and soaking unit removes larger food residues on the tableware through a rotary brush or a scraper according to the control command and the predetermined operating parameters, flushes with high-pressure water, and then puts it into the soaking tank for soaking to soften the oil stains and stubborn stains, and transmits it to the spray rinsing unit;

[0060] S63. The spray rinsing unit sprays high-temperature and high-pressure water flow through the nozzle and rinses multiple times according to the control command and the predetermined operating parameters to remove the surface oil stains and residual detergent, avoiding harm to human health, and transmits it to the disinfection and drying unit;

[0061] S64. After rinsing, the disinfection and drying unit kills surface bacteria and viruses through multiple disinfections according to the control command and the predetermined operating parameters, and uses hot air drying to remove the surface water marks to ensure that the tableware is dry without water stains, and transmits it to the appearance detection unit;

[0062] S65. The appearance detection unit obtains the appearance information and odor information of the surface of the tableware after dishwashing through the set high-definition camera and odor sensor respectively to ensure that the hygiene of the tableware surface meets the dishwashing quality standard, and transmits it to the hygiene detection unit;

[0063] S66. The hygiene detection unit detects the hygiene index data of the surface of the tableware after dishwashing, such as the hygiene index, cleaning index, and drying index, through the tableware and chopsticks detector to ensure that the quality of the dishwasher meets the requirements, and transmits it to the processing center;

[0064] S67. The processing center compares the quality information of the dishwasher with the dishwasher washing quality standard stored in the memory: if it meets the standard, it notifies that the dishwashing is completed; if it does not meet the standard, it transfers it to the alarm and notifies rework or repair.

[0065] A dishwasher control system based on AI technology provided by the present invention further includes a computer-readable storage medium containing a memory; the memory stores a computer program, and when each functional module executes the computer program, it realizes the steps of an automatic control method for a dishwasher based on AI technology as described in any one of the above; a computer program is stored on the computer-readable storage medium, and when the computer program is executed by each functional module, it realizes the steps of an automatic control method for a dishwasher based on AI technology as described in any one of the above.

[0066] The present invention also provides a dishwasher based on AI technology, which is realized by using the automatic control method for a dishwasher based on AI technology as described above.

[0067] Advantages of the present invention compared with the prior art:

[0068] By setting up various functional modules such as an information acquisition module, a model construction module, a model training module, a model evaluation module, a parameter determination module, and an application control module, early prevention is carried out by collecting abnormal phenomena during daily dishwashing, preset control parameters are set, automatic identification and control are performed, and AI artificial intelligence and Internet of Things technology are incorporated. It has functions such as Wi-Fi connection, remote control, and intelligent adjustment, and can automatically adopt different cleaning processes according to different tableware, thereby saving energy and protecting the environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0069] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required for use in the embodiments or exemplary technical descriptions. Obviously, the following drawings are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0070] Figure 1 It is a schematic diagram of the system module of the present invention;

[0071] Figure 2 It is a schematic diagram of the information acquisition module of the present invention;

[0072] Figure 3 It is a schematic diagram of the model construction module of the present invention;

[0073] Figure 4 It is a schematic diagram of the model training module of the present invention;

[0074] Figure 5Schematic diagram of the model evaluation module of the present invention;

[0075] Figure 6 Schematic diagram of the parameter determination module of the present invention;

[0076] Figure 7 Schematic diagram of the application control module of the present invention;

[0077] Figure 8 Schematic diagram of the method process control program of the present invention;

[0078] Figure 9 Schematic diagram of the program of step S10 in the method process of the present invention;

[0079] Figure 10 Schematic diagram of the program of step S20 in the method process of the present invention;

[0080] Figure 11 Schematic diagram of the program of step S30 in the method process of the present invention;

[0081] Figure 12 Schematic diagram of the program of step S40 in the method process of the present invention;

[0082] Figure 13 Schematic diagram of the program of step S50 in the method process of the present invention;

[0083] Figure 14 Schematic diagram of the program of step S60 in the method process of the present invention. Detailed implementation manners

[0084] In order to make the objectives, technical solutions and advantages of the present invention clearer and more understandable, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0085] The following describes the specific implementation of the present invention in detail with reference to specific embodiments:

[0086] In order to make the technical problems, technical solutions and beneficial effects to be solved by the present application clearer and more understandable, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application. It should be noted that when a module is referred to as being "disposed on" another module, it can be directly on the other module or indirectly on the other module. When a module is referred to as being "connected to" another module, it can be directly connected to the other module or indirectly connected to the other module.

[0087] In the description of the present application, the meaning of "a plurality of" is two or more, unless otherwise specifically defined. The meaning of "several" is one or more, unless otherwise specifically defined.

[0088] In the description of the present application, it should be noted that unless otherwise clearly specified and limited, the terms "connected" and "coupled" 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 directly connected or indirectly connected through an intermediate medium, and it can be the communication inside two components or the interaction relationship between two components. For those of ordinary skill in the art, the specific meanings of the above terms in the present application can be understood according to specific situations. The terms "comprising", "including", "having" and their variants all mean "including but not limited to", unless otherwise particularly emphasized in other ways.

[0089] Please refer to Figure 1 As shown, the present invention provides an automatic control method for a dishwasher based on AI technology, which is applied to a dishwasher control system based on AI technology. The system includes an information acquisition module, a model construction module, a model training module, a model evaluation module, a parameter determination module, an application control module, a wireless communication module, a memory, an alarm, a processing center, and a smart mobile terminal. The information acquisition module, the model construction module, the model training module, the model evaluation module, the parameter determination module, the application control module, the wireless communication module, the memory, and the alarm are respectively connected to the processing center. The smart mobile terminal includes a smart phone, a tablet computer, and a smart remote control, and is wirelessly connected to the wireless communication module within the range of a wireless network or the Internet.

[0090] The wireless communication module is provided with a wireless network unit, which is responsible for the transceiver of wireless signals and automatically forms a network connection with the smart mobile terminal within an effective network range. The wireless signals include various Internet of Things signals such as MQTT, CoAP, HTTP, REST API, Zigbee, LoRaWAN, NB-IoT, and Bluetooth.

[0091] The alarm compares the actual evaluation score of the model with the model evaluation score standard stored in the memory. If the standard is not met, it will automatically give an audible alarm and notify to continue training. It also compares the quality information of the dishwasher with the dishwasher washing quality standard stored in the memory. If the standard is not met, it will automatically give an audible alarm and notify to adjust the parameters and rework. It further compares the quality information of the dishwasher with the dishwasher washing quality standard stored in the memory. If the standard is not met, it will automatically give an audible alarm and notify to rework or repair again.

[0092] The memory is responsible for storing information of the information acquisition module, model construction module, model training module, model evaluation module, parameter determination module, application control module, wireless communication module, and alarm, as well as storing the model evaluation sub-criteria and the dishwashing quality standard of the dishwasher.

[0093] The processing center is responsible for information transfer among each functional module, alarm, and memory, and is the hub center of the system. It compares the actual model evaluation score with the model evaluation sub-criteria stored in the memory: if it meets the standard, it is the predetermined dishwasher control parameter; if it does not meet the standard, it is transmitted to the alarm and notifies to continue training. It also compares the dishwasher quality information with the dishwasher dishwashing quality standard stored in the memory: if it meets the standard, it is set as the formal dishwashing control parameter; if it does not meet the standard, it is transmitted to the alarm and notifies to adjust the parameters and rework. It further compares the dishwasher quality information with the dishwasher dishwashing quality standard stored in the memory: if it meets the standard, it notifies that the dishwashing is completed; if it does not meet the standard, it is transmitted to the alarm and notifies to rework or repair again.

[0094] Please refer to Figure 2 As shown, the information acquisition module includes a data acquisition unit, a cleaning data unit, an enhancement data unit, an integration data unit, a conversion data unit, a filtering and denoising unit, a grayscale conversion unit, and a feature extraction unit, which is responsible for acquiring normal and abnormal historical image data produced by the dishwasher, preprocessing them, and transmitting them to the model construction module.

[0095] Furthermore, the data acquisition unit obtains historical data of the cleaning effects and their control parameters of similar dishwashers on different tableware in terms of dirt degree, quantity, and type by connecting to an industry database, and transmits it to the cleaning data unit; the cleaning data unit cleans the collected dishwashing historical data to remove outliers, duplicate values, or missing values in the data, and transmits it to the enhancement data unit; the enhancement data unit increases the quantity and diversity of dishwashing training data through data enhancement methods such as rotation, scaling, flipping, cropping, and color transformation, and transmits it to the integration data unit; the integration data unit obtains standardized dishwashing data according to the data standardization processing formula "z=(x - μ) / σ", and transmits it to the conversion data unit; the conversion data unit obtains normalized dishwashing data according to the normalization calculation formula "x'=(x - min(x)) / (max(x)-min(x))", and transmits it to the filtering and denoising unit; the filtering and denoising unit is based on the Gaussian filtering method calculation formula Obtain the denoised dishwashing image and transfer it to the grayscale conversion unit; the grayscale conversion unit obtains the grayscale dishwashing image according to the grayscale calculation formula "f(i,j) = max(R(i,j), G(I,j), B(i,j))" and transfers it to the feature extraction unit; the feature extraction unit converts the labeled data into feature vectors useful for model training and extracts the key features of appearance cleanliness, dryness, and hygiene indicators to improve the training speed and performance of the model.

[0096] Please refer to Figure 3 As shown, the model construction module includes a network layer unit, a network parameter unit, a hierarchical optimization unit, and a data partitioning unit, which are responsible for constructing the model by determining the model architecture, designing the network layer structure, adding auxiliary layers, and defining model parameters according to the extracted feature information, and transferring it to the model training module.

[0097] Furthermore, the network layer unit customizes and optimizes the network layer structure according to the selected convolutional neural network as the model architecture and based on specific application scenarios and requirements, and transfers it to the network parameter unit; the network parameter unit adjusts the number of network layers, the size of the convolutional kernel, the stride, the padding method, and selects the loss function and optimization algorithm according to the network layer structure, and transfers it to the hierarchical optimization unit; the hierarchical optimization unit adjusts the size of the input data and performs normalization processing by adding zero-padding layers and normalization layers before and after the convolutional layer respectively, and transfers it to the data partitioning unit; the data partitioning unit divides the dataset with the extracted key feature vectors into a training set, a validation set, and a test set and establishes a convolutional neural network structure for subsequent model training.

[0098] Please refer to Figure 4 As shown, the model training module includes an input padding unit, a convolutional input unit, a pooling conversion unit, a fully connected layer unit, a normalized output unit, an output conversion unit, and a backpropagation unit, which are responsible for training the model according to the collected data, adjusting the model parameters to optimize the model performance to the predetermined dishwasher control parameters, and transferring it to the model evaluation module.

[0099] Furthermore, the input padding unit is based on the data padding size calculation formula "P H = [(Ho - 1) * S H + K H - H i / 2, P W = [(Wo - 1) * S W + K W-Wi] / 2” obtains the filled data and inputs it, and transfers it to the convolution input unit; the convolution input unit obtains the convolution input value according to the convolution input calculation formula "z(t) = ∫x(m)y(t - m)dm" and activates the function input, and transfers it to the pooling conversion unit; the pooling conversion unit obtains the maximum pixel value after pooling according to the maximum pooling calculation formula "Z(i,j) = max(X[i*P S (i + 1)*P S ,j*P S (j + 1)*P S )" and enters the fully connected layer, and transfers it to the fully connected layer unit; the fully connected layer unit obtains the output data of the connection layer according to the fully connected layer calculation formula "y = f(∑(w n *x n ) + b)" and enters the output layer, and transfers it to the normalization output unit; the normalization output unit obtains the output of the Batch Norm according to the Batch Norm layer calculation formula "h = φ(B N (Wx + b))" and transfers it to the output conversion unit; the output conversion unit obtains the size of the output value after convolution according to the output layer conversion calculation formula "N = (P - F + 2C) / S + 1" and transfers it to the backpropagation unit; the backpropagation unit obtains the loss function value according to the loss function calculation formula "L = max(0, m + y*(f(x) - b))" and performs backpropagation to optimize the performance of the network model.

[0100] Please refer to Figure 5 As shown, the model evaluation module includes a classification marking unit, a learning and training unit, and a model evaluation unit, which are responsible for validating and evaluating the model according to the trained model, adjusting and optimizing the model according to the verification results, and transferring it to the parameter determination module.

[0101] Furthermore, the classification marking unit divides and marks the corresponding data sample categories according to the abnormal categories of dishwashing quality and transfers them to the learning and training unit; the learning and training unit determines the training model according to the gradient descent data, inputs the data in the training set into the model for simulation training under different environmental conditions, and transfers it to the model evaluation unit; the model evaluation unit obtains the comprehensive F evaluation score according to the model evaluation score calculation formula "F = 2(Ac*Re) / (Ac + Re)" and transfers it to the processing center.

[0102] Please refer to Figure 6 As shown, the parameter determination module includes a cleaning power consumption unit, a cleaning water consumption unit, a trial debugging unit, and an anomaly recognition unit, which are responsible for conducting cleaning tests on different tableware according to the dishwashing control parameters predicted by the trained model to obtain the optimal dishwasher control parameters and transfer them to the application control module.

[0103] Further, the cleaning power consumption unit obtains the power consumption of dishwashing, cleaning, and drying according to the dishwashing power consumption calculation formula "E = P1*T1 + P2*T2" and transmits it to the cleaning water consumption unit; the cleaning water consumption unit obtains the water consumption of dishwashing, cleaning, and drying according to the dishwashing water consumption calculation formula "W = πR 2 *υ*T1" and transmits it to the trial debugging unit; the trial debugging unit conducts cleaning tests on different tableware through the dishwasher according to the preset dishwashing control parameters, detects and obtains the cleaning quality information, and transmits it to the processing center; the anomaly recognition unit matches the real-time obtained dishwasher operation image with the corresponding image in the trained convolutional neural network model and confirms its anomaly category for subsequent improvement of the dishwashing process and parameter adjustment.

[0104] Please refer to Figure 7 As shown, the application control module includes a category acquisition unit, a slag removal and soaking unit, a spray rinsing unit, a disinfection and drying unit, an appearance detection unit, and a hygiene detection unit, which are responsible for controlling the dishwasher for dishwashing according to the set dishwashing control parameters and program instructions and conducting various quality inspections to ensure that the dishwasher meets the quality requirements after automatic dishwashing.

[0105] Further, the category acquisition unit obtains the material and oil stain degree of the tableware to be cleaned through a high-definition camera, combines the washing requirements with the model to match the corresponding washing program, and transmits it to the slag removal and soaking unit; the slag removal and soaking unit removes larger food residues on the tableware through a rotating brush or scraper according to the control command and preset operation parameters, flushes it with high-pressure water, and then puts it into the soaking tank for soaking, and transmits it to the spray rinsing unit; the spray rinsing unit sprays high-temperature and high-pressure water through a nozzle according to the control command and preset operation parameters and rinses it multiple times to remove surface oil stains and residual detergents, and transmits it to the disinfection and drying unit; after rinsing, the disinfection and drying unit kills surface bacteria and viruses through multiple disinfections according to the control command and preset operation parameters, and uses hot air drying to remove surface water stains, and transmits it to the appearance detection unit; the appearance detection unit obtains the appearance information and odor information on the surface of the tableware after dishwashing through the set high-definition camera and odor sensor respectively, and transmits it to the hygiene detection unit; the hygiene detection unit detects the hygiene index data of the surface of the tableware after dishwashing, such as the hygiene index, cleaning index, and drying index, through a tableware and chopstick detector to ensure that the quality of the dishwasher meets the requirements, and transmits it to the processing center.

[0106] System operation principle:

[0107] Before application, the information acquisition module acquires the historical image data of normal and abnormal production of the dishwasher and performs preprocessing for subsequent model construction, and transmits it to the model construction module; then the model construction module determines the model architecture, designs the network hierarchical structure, adds auxiliary layers, and defines model parameters according to the extracted feature information to construct the model for subsequent model training and verification, and transmits it to the model training module; the model training module trains the model according to the collected data and adjusts the model parameters to optimize the model performance to the predetermined dishwasher control parameters to ensure the quality stability of the dishwasher operation, and transmits it to the model evaluation module; then the model evaluation module verifies and evaluates the model according to the trained model, and adjusts and optimizes the model according to the verification results to improve the performance and accuracy of the model, and transmits it to the parameter determination module; then the parameter determination module conducts cleaning tests on different tableware according to the dishwashing control parameters predicted by the trained model to obtain the optimal dishwasher control parameters to ensure the subsequent dishwashing quality, and transmits it to the application control module; the application control module controls the dishwasher for dishwashing according to the set dishwashing control parameters and program instructions and conducts various quality inspections to ensure that the dishwasher meets the quality requirements after automatic dishwashing.

[0108] When the user or manager is outdoors or in a foreign place, they can use the intelligent mobile terminal to automatically form a network connection with the wireless communication module within the wireless network or the Internet, realizing the combination of the intelligent mobile terminal, the Internet and the Internet of Things technology. Through the APP software on the intelligent mobile terminal or the remote control software on the computer, the user can perform close-range or remote control of the dishwasher operation to meet the quality requirements of the user. The user or manager can remotely control and monitor the operation of the dishwasher, view the daily operation status, data change status, device activity logs, etc. By means of prefabricated deployment codes or adding deployment codes, remote connection and control of the dishwasher operation can be realized. The operation of the remote dishwasher can be viewed in real time through both the intelligent mobile terminal and the computer. For the large-scale catering industry, it not only improves the management efficiency but also reduces the management cost.

[0109] Please refer to Figure 8 As shown in the figure, a dishwasher automatic control method based on AI technology provided by the present invention includes the following steps:

[0110] S10. Before application, the information acquisition module acquires the historical image data of normal and abnormal production of the dishwasher and performs preprocessing for subsequent model construction, and transmits it to the model construction module;

[0111] Please refer to Figure 9 As shown in the figure, the step S10 includes the following steps:

[0112] S11. The data acquisition unit obtains historical data on the dirtiness levels, quantities, types of different tableware, the cleaning effects after being cleaned by similar dishwashers, and their control parameters by connecting to the industry database, and transfers it to the cleaning data unit;

[0113] For further illustration, the control parameters of dishwashing by similar dishwashers are collected from domestic and foreign dishwashing databases through a data collector, as well as the quality information of the corresponding images or videos after dishwashing and the data on the usage effects of different users are classified and aggregated; the quality data after dishwashing by the dishwashers includes, but is not limited to, the historical data of the usage effect evaluations of different users on different such dishwashers, and also includes the normal and abnormal quality information of similar dishwashers and the historical data of the usage effects of different users obtained through web crawling, sensor collection, manual annotation, dataset purchase, crowdsourcing, etc. from third-party sharing platforms such as the Internet, social media, professional testing institutions, food service industry platforms, public datasets, etc., so as to obtain high-quality, diverse and rich historical data after dishwashing by similar dishwashers, specifically including historical data of quality information such as tableware data, dishwashing operation parameters, dishwashing process parameters, dishwashing detection data and images; the raw material data includes the shape diagrams and processing diagrams and data of the electronic components of various dishwashers; the tableware data includes: the dirtiness level of the tableware to be washed obtained through sensors, the quantity of the tableware sensed through sensors, and different types of tableware such as glassware, ceramic bowls and plates, metal tableware, etc. automatically identified through intelligent recognition technology; the dishwashing operation parameters include washing mode, dosage of detergent, placement of tableware, water temperature, drying method, etc.; the dishwashing process parameters include water temperature, cleaning time, water pressure, flushing method, cleaning index, drying index, etc.; the detection data includes cleaning index, drying index, power consumption, water consumption, cleaning time, antibacterial and sterilization, noise, trouble-free operation time, etc.

[0114] S12. The cleaning data unit cleans the collected dishwashing historical data to remove outliers, duplicate values or missing values in the data, so as to improve the quality and accuracy of the data, and transfers it to the enhanced data unit;

[0115] Further explanation: Due to sensor failures, recording errors, or system anomalies during the operation of the dishwasher, outliers may occur, affecting the accuracy of subsequent analysis; missing value processing is performed on the dishwashing data with missing parts; by writing code to detect each feature in the dataset to determine missing values and identify missing value patterns, and according to the number and impact of missing values, write code to select whether to fill or delete samples or variables containing missing values. For time series data, forward filling or backward filling is used to fill in the missing values; the processing effect is verified by comparing indicators such as data quality, model accuracy, and reliability before and after processing. If the processing effect is not good, reselect the processing method or re-clean the data until the best effect is achieved, so as to remove duplicate, incorrect, and invalid data to effectively process missing values for subsequent model construction and analysis.

[0116] S13. The enhanced data unit uses data augmentation methods such as rotation, scaling, flipping, cropping, and color transformation to increase the quantity and diversity of dishwashing training data, improve the generalization ability of the model, and transfer it to the integrated data unit;

[0117] Further explanation: When the washed dishwashing image data is rotated through dishwashing image data rotation, rotating by a certain angle will cause multiple pixels to correspond to the same pixel after rotation, resulting in the loss of pixels in the rotated dishwashing image data. Therefore, a reverse thinking is used to construct a mapping to map the pixel coordinates after rotation to the pixel coordinates of the original dishwashing image data, so as to ensure that each pixel after rotation has a pixel value; the neighborhood interpolation algorithm is used to copy each original pixel in the rotated dishwashing data unchanged to the corresponding four pixels after expansion, retaining all the information of the original dishwashing image data; the dishwashing image data with abnormal orientation after scaling is flipped 180 degrees around the center axis or symmetry axis of the original image to ensure the orientation consistency of the dishwashing data; the rotated dishwashing image data is cropped to ensure the integrity and clarity of the image.

[0118] S14. The integrated data unit obtains the standardized dishwashing data according to the data standardization processing formula "z=(x - μ) / σ, where z is the standardized data, x is the original data, μ is the mean of the data, and σ is the standard deviation of the data" to improve the stability of the model and transfer it to the conversion data unit;

[0119] Further explanation: Calibrate the original dishwashing data collected, including time synchronization, unit conversion, range adjustment, etc. For example, ensure that all timestamps are in a unified format and synchronized with the system clock; convert the data collected by different sensors, detection devices, etc. to the same unit to ensure data accuracy; use the above data standardization processing formula "z=(x - μ) / σ" through the written code to convert data from different sources such as dates, values, texts, etc. into a standard normal distribution with a mean of 0 and a standard deviation of 1, subtract the mean and divide by the standard deviation to make it in a unified standard format to ensure data consistency and comparability for subsequent processing; encode unstructured data to convert it into structured data, or convert text data into numerical representations for easy model processing and analysis, so as to process the original data into a form that meets specific standards for subsequent model training and analysis.

[0120] S15. The data conversion unit obtains the normalized dishwashing data according to the normalization calculation formula "x'=(x - min(x)) / (max(x)-min(x)), where x' is the normalized data, x is the original data, and min(x) and max(x) are the minimum and maximum values of the data respectively" to improve the model performance and transmit it to the filtering and denoising unit;

[0121] Further explanation: Through the written code, use the above normalization calculation formula "x'=(x - min(x)) / (max(x)-min(x))" to proportionally map and scale the cleaned data to the specified range of [0,1], convert the data into a unified format or range for data normalization, and perform data discretization such as converting continuous features into discrete features to transform the data, so as to eliminate the total difference between different samples or features and the dimensionality impact between data, make the data distribution consistent, and confirm whether the data has been normalized to the specified range or distribution as expected, and verify the normalization effect through statistical descriptions such as maximum and minimum values; The dishwashing data includes various types such as texts, pictures, audios, videos, etc. to eliminate the dimensionality differences between different data, thereby improving the accuracy and efficiency of data analysis to better adapt to subsequent analysis and processing.

[0122] S16. The filtering and denoising unit obtains the denoised dishwashing image according to the Gaussian filtering method calculation formula " G(x,y) is the pixel of the two-dimensional Gaussian function, (x,y) is the pixel coordinate, and σ is the standard deviation" for grayscale image conversion and transmits it to the grayscale conversion unit;

[0123] Further explanation: The Gaussian filter output pixel value obtained according to the Gaussian filter calculation formula is the weighted average of the input pixel values in its neighborhood, and the weights are given by the Gaussian function. Among them, the standard deviation σ determines the width of the Gaussian function, and the Gaussian function is discretized, that is, the weights are calculated within a certain window size, and then these weights are applied to the corresponding neighborhood pixel values of the input image to obtain the output pixel values. The pixels are arranged in ascending order according to the gray value, and the median value is taken as the new gray value; the sampling values in the input signal are checked to determine whether they represent the signal itself. By using an observation window composed of an odd number of samplings, the values within the window are sorted, the median value is taken as the output, the earliest value is discarded, and a new sampling is obtained. The above calculation process is repeated to reduce the random noise in the image and make the dishwashing image smoother.

[0124] S17. The grayscale conversion unit obtains the grayscale dishwashing image according to the grayscale calculation formula "f(i,j) = max(R(i,j), G(i,j), B(i,j)), where f(i,j) is the image after grayscale, and R(i,j), G(i,j), B(i,j) are the original images of the three colors" for subsequent feature extraction and transmits it to the feature extraction unit;

[0125] Further explanation: The grayscale dishwashing image is obtained through the grayscale calculation formula. The sampling values in the input signal are checked to determine whether they represent the signal itself. By using an observation window composed of an odd number of samplings, the values within the window are sorted, the median value is taken as the output, the earliest value is discarded, and a new sampling is obtained. The above calculation process is repeated to remove the noise in the dishwashing image or other signals for subsequent extraction of the key features of the dishwashing image, including information such as appearance cleanliness, dryness, and hygiene indicators; then the standardized data is classified through the written code, and the classified data is automatically labeled to add accurate labels or annotations to the data, which are used as the target variables or features during subsequent model training, so as to be used as the training set and validation set, ensuring that the model has accurate data reference during the training process and enabling it to learn how to generate corresponding labels according to the data features to improve the labeling efficiency and accuracy; for some data, users need to remotely add new labels or modify existing labels through the mobile phone to ensure that they accurately reflect the essential features of the data. The marked data is deployed to the corresponding system platform for subsequent application or analysis to improve the accuracy and reliability of the labels, facilitating the extraction of key features in the subsequent data and being more conducive to model training, testing, and validation.

[0126] S18. The feature extraction unit converts the labeled data into feature vectors useful for model training and extracts the key features of appearance cleanliness, dryness, and hygiene indicators to improve the training speed and performance of the model.

[0127] It is further explained that the most representative features and the most useful features for the model that can reflect the essential content of the data and have the degree of discrimination and description are selected from the dishwashing data after preprocessing to reduce the dimension of the features, reduce the computational complexity, and improve the performance and generalization ability of the model; after feature extraction, principal component analysis is used to perform feature dimensionality reduction to obtain a large amount of feature information in order to reduce the dimension of the features and reduce the computational complexity; after feature dimensionality reduction, the features are binary encoded to improve the interpretability of the features and the performance of the model; since some information of the original data may be lost after feature extraction and dimensionality reduction, feature reconstruction such as principal component reconstruction or least squares reconstruction is performed to restore the data information as much as possible; evaluation is performed through cross-validation, and the feature extraction method and parameters are adjusted according to the evaluation results to evaluate the quality and effect of the extracted features, improve the training speed and performance of the model, and improve the efficiency of data analysis by reducing the amount or complexity of the data while keeping the original appearance of the data as much as possible.

[0128] S20, the model building module determines the model architecture, designs the network hierarchy, adds auxiliary layers, and defines model parameters according to the extracted feature information to build the model for subsequent model training and verification, and passes it to the model training module;

[0129] See also Figure 10 As shown, the step S20 comprises the following steps:

[0130] S21, the network level unit customizes the design and optimizes the network level structure according to the selected convolutional neural network as the model architecture and the specific application scenarios and requirements for subsequent defect detection and quality identification, and passes it to the network parameter unit;

[0131] Further explanation: Since the convolutional neural network (CNN) is a type of deep neural network, which is particularly suitable for processing data with a grid topology structure, it can automatically learn and extract useful features such as edges, lines, corners, and more complex combined features from images during the operation of the dishwasher for subsequent defect detection, quality classification, etc. Since the basic structure of the CNN consists of an input layer, a convolutional layer, an activation function layer, a pooling layer, a fully connected layer, and an output layer, these levels can work together in the CNN model for dishwasher production to extract and process image features, including: the input layer can receive the image data of the dishwasher as input; the convolutional layer sets multiple convolutional layers, each containing multiple convolutional kernels, which can extract local features in the image. As the network structure deepens, it gradually becomes more abstract from the appearance; adding a ReLU activation function layer after the convolutional layer can introduce non-linear factors and enhance the expressive ability of the model; adding a pooling layer after the convolutional layer can reduce the dimension of the feature map, reduce the amount of calculation, and at the same time maintain the spatial invariance of important features; adding a fully connected layer at the end of the network is used to convert the feature maps output by the convolutional layer and the pooling layer into classification results, that is, the category or quality level of the dishwasher.

[0132] S22. The network parameter unit adjusts the number of network layers, the size of the convolutional kernel, the stride, the padding method, and selects the loss function and the optimization algorithm according to the network hierarchical structure to ensure the performance and accuracy of the model, and transmits them to the hierarchical optimization unit;

[0133] Further explanation: Defining model parameters according to the network hierarchical design, including the size of the convolutional kernel, the stride, the padding method, the activation function, etc., as well as the pooling method of the pooling layer, the size of the pooling window, etc., and the number of neurons in the fully connected layer, etc. These hierarchical parameters directly affect the performance and accuracy of the model; then set hyperparameters related to model training such as the size of the input image, the number of label types, the total number of training cycles, the batch size, etc., and adjust them according to the specific dataset and task requirements; select optimization algorithms such as SGD, Adam, etc., and set corresponding parameters such as the learning rate, momentum, etc., which directly affect the training effect and convergence speed of the model to ensure that the model can accurately extract features from images and perform effective classification or prediction.

[0134] S23. The hierarchical optimization unit adjusts the size and normalization processing of the input data by adding a zero-padding layer and a normalization layer before and after the convolutional layer respectively to improve the model training speed and stability, and transmits them to the data partitioning unit;

[0135] Further explanation: By setting a zero-padding layer to perform zero-padding on the edges of the input image before the convolution operation, the size of the input data is adjusted to facilitate the convolution operation, preserve the image edge information, ensure that the convolution kernel can be correctly applied to the image boundary, and at the same time help to maintain the image edge information and avoid information loss during the convolution process; zero-padding can more effectively process input images of different sizes without the need for complex preprocessing, help control the size of the output feature map of the convolution layer, make the network design more flexible and controllable, ensure that the network can adapt to dishwashers of different sizes and resolutions, and accurately extract and process image features; normalize the distribution of the input data to improve the training speed and stability of the model, accelerate the training process of the neural network and improve the convergence speed, while enhancing the stability of the model. Normalize the input of the activation function before the activation function of each layer of the network. Calculate the mean and variance of this batch for each small batch of data, and then perform batch normalization on the linear calculation results, that is, subtract the mean and divide by the standard deviation to ensure that the calculation results conform to the standard normal distribution with a mean of 0 and a variance of 1, and then perform translation and scaling operations to adapt to different data distribution requirements, keep the input of the middle layer of the network relatively stable, help solve the problem of gradient disappearance or gradient explosion during the training process, thereby accelerating the training and enhancing the stability of the model, and can improve the robustness of the model to the weight initialization method, reduce the trouble caused by the weight initialization selection, and improve the generalization ability and training efficiency of the model.

[0136] S24. The data division unit divides the dataset with key feature vectors after extraction into a training set, a validation set, and a test set and constructs a convolutional neural network structure for subsequent model training.

[0137] Further explanation: According to the preselected segmentation strategy, determine the proportions of the training set, validation set, and test set, and ensure that the data distributions among the subsets are as consistent as possible to avoid introducing biases. In some application scenarios, due to the time-series characteristics of the data, write code to divide the dataset into a training set for training the model, a validation set for adjusting model parameters and selecting the best model, and a test set for evaluating the final performance of the model according to the time series, to ensure the temporal consistency between the training and test sets. Establish a training set and a test set required for predicting the dishwasher quality anomaly recognition pattern in different environments through the convolutional neural network deep learning method with a 9:1 relationship of the dataset, thereby establishing a deep convolutional neural network structure: 3 convolutional layers, 3 max pooling layers, 2 fully connected layers, 1 softmax layer, and 1 output layer. Add zero-padding layers and normalization layers when necessary. Since the convolutional kernels in the convolutional layers contain weight coefficients while the pooling layers do not, the pooling layers are not independent layers. The convolutional layers are used to extract local features of the image, the pooling layers are used to reduce the dimension of the feature map, and the fully connected layers are used to integrate features and perform classification.

[0138] S30. The model training module trains the model based on the collected data, adjusts the model parameters to optimize the model performance to the predetermined dishwasher control parameters, ensures the stability of the dishwasher operation quality, and transmits it to the model evaluation module.

[0139] Please refer to Figure 11 As shown, step S30 includes the following steps:

[0140] S31. The input padding unit obtains the padding data according to the data padding size calculation formula "P H =[(Ho - 1)*S H +K H -H i / 2, P W =[(Wo - 1)*S W +K W -Wi] / 2, P H , P W are the padding sizes in the height / width directions respectively, Hi and Wi are the height / width of the input feature map respectively, K H , K W are the height / width of the convolutional kernel respectively, S H , S W are the values of the stride in the height / width directions respectively, and Ho and Wo are the height and width of the output feature map respectively", inputs the obtained padding data, and transmits it to the convolutional input unit.

[0141] Further explanation: After normalizing the image, the dishwashing data first enters the input layer. The padding data is obtained through the above-mentioned padding size calculation formula and enters the zero-padding layer, which pads zero values to the edges of the input data of the convolutional layer, adjusts the size of the input data for convolution operations, and maintains the same spatial dimension of the input and output to prevent the loss of image edge information, so that the spatial dimension of the input data remains unchanged during subsequent convolution operations, thereby maintaining the image edge information and the processing of subsequent layers; the number of padding is jointly determined by the size of the convolutional kernel, the stride, and the padding size. To keep the height and width of the input and output images the same, or to reduce the rapid reduction of size during consecutive convolution operations, the number is usually set to the convolutional kernel size minus; the height Hi / width Wi of the input feature map, the height K H / width K W and the stride value S H / S W in the height / width direction. The height Ho / width Wo of the output feature map are both obtained through the model design parameters.

[0142] S32. The convolution input unit obtains the convolution input value according to the convolution input calculation formula "z(t) = ∫x(m)y(t - m)dm, where z(t) is the output function, x(t) is the input function, y(t) is the convolution kernel function, and dm is the integration element for the variable m", activates the function input, and passes it to the pooling conversion unit;

[0143] Further explanation: The "width" or "increment" of the integration element dm when integrating each infinitesimal interval of the variable m is used to obtain the cumulative effect z(t) over the entire domain by accumulating the function values (i.e., x(m)y(t - m)) on these infinitesimal intervals. dm is the integration element for the variable m, that is, the infinitesimal quantity in the integration process; and the convolution calculation is performed to obtain the convolution value, which enters the convolutional layer and passes through the ReLU function calculation formula "f(x) = max(0, x + Y)" to obtain the activation function value and enter the activation function layer. In the formula, f(x) is the activated function, x is the feature value output by the convolutional layer or the fully connected layer, and Y is a random variable. When the input x is greater than 0, then x is output. When the input x is less than or equal to 0, then 0 is output. When x = 0, it is non-differentiable, that is, when the input is positive, the original value is maintained, and when the input is negative, 0 is output; however, the ReLU activation function is used after the convolutional layer to increase the non-linearity of the network and promote the model to learn complex patterns.

[0144] S33. The pooling conversion unit calculates according to the max-pooling calculation formula "Z(i,j) = max(X[i*P S (i + 1)*P S ,j*P S (j + 1)*P S),Z(i,j) is a pixel value in the output feature map after pooling, where i and j are the positions in the output feature map respectively, max is to find the maximum value among all pixel values in the input window, X is the input feature map, and P S is the window size of the pooling operation. The maximum pixel value after pooling enters the fully connected layer to retain important feature information and is passed to the fully connected layer unit;

[0145] Furthermore, by calculating the average value of all values in each region through the above maximum pooling calculation formula as the output, more information in the feature map can be retained, which helps to improve the accuracy of the model, retains more detailed information, and is used in the deeper layers of the network to ensure the integrity of information; Before maximum pooling, according to the average pooling calculation formula "Z(i,j) = mean(X[i*P S (i + 1)*P S , j*P S (j + 1)*P S )", the maximum pixel value after average pooling is obtained. Z(i,j) is a pixel value in the output feature map after pooling, mean is to find the average value among all pixel values in the input window, and according to this formula, the maximum value in each region of the input feature map is selected as the output, retaining the most significant features in the feature map, reducing the size of the feature map, and losing some useful information. Since the maximum value in each region is concerned, the grain size feature is retained, and features with better classification recognition are selected.

[0146] S34. The fully connected layer unit obtains the output data of the connection layer according to the fully connected layer calculation formula "y = f(∑(wn*xn)+b), where y is the output result, f is the activation function, wn is the weight of the nth input feature, xn is the n input features, n is the dimension of the input features, and b is the bias", and enters the output layer for subsequent output calculation and is passed to the normalized output unit;

[0147] Furthermore, after pooling, the data is passed through the fully connected layer. According to the fully connected layer calculation formula "y = f(∑(w n *x n )+b)", the output value after convolution is calculated. In the formula, y is the output result, f is the activation function, w n is the weight of the nth input feature, x n is the n input features, n is the dimension of the input features, and b is the bias; The "y = f(∑(w n *x n )+b)" is deduced from "y = f(w*x+b)" to "y = f(w 1 *x 1 +w 2 *x 2+…+wn*xn+b)” and is transformed from it, where w is the weight and x n is the input feature; the features extracted by the convolutional layer and the pooling layer are integrated and classified through the fully connected layer, so that each neuron is connected to all neurons in the previous layer, and the output is generated through weighted summation and non-linear activation function.

[0148] S35. The normalized output unit obtains the output of Batch Norm according to the Batch Norm layer calculation formula "h = φ(B N (Wx + b)), where h is the output of the fully connected layer, φ is the activation function, B N is the operator for batch normalization, W is the weight parameter, x is the input of the fully connected layer, and b is the bias parameter", and passes it to the output conversion unit;

[0149] Further explanation, the "h = φ(B N (Wx + b))" is deduced from "B N (x) = γ ⊙ [(x - μ B ) / σ B + β", where μ B is the mean, σ B is the standard deviation, γ is the stretching parameter, β is the offset parameter, and (x - μ B ) / σ B is the standardized normal distribution; the Batch Norm layer (abbreviated as "BN layer") is placed between the affine transformation and the activation function in the fully connected layer, standardizes the output values of each layer in the network, makes it more conform to the normal distribution, can accelerate the training speed of the neural network, helps to prevent gradient disappearance and gradient explosion; the BN layer reduces the correlation between input data by standardizing each mini-batch of data, makes the mean of each sample 0 and the variance 1, thus reducing the problem of internal covariate shift, helps to accelerate the training process, improves the stability and generalization ability of the model, and avoids the problem of reducing the representation ability of the neural network.

[0150] S36. The output conversion unit obtains the size of the output value after convolution according to the output layer conversion calculation formula "N = (P - F + 2C) / S + 1, where N is the size of the output after convolution, P is the size of the input before convolution, F is the size of the convolution kernel, C is the number of layers of adding 0 around the image, and S is the step size", for subsequent model analysis and training, and passes it to the backpropagation unit;

[0151] Further explanation, the output size N is the size of the feature map after convolution operation, the input size P is the width or height of the input image or feature map, and the padding size P in the height direction and the padding size P in the width direction are respectively obtained through the above step S21 calculation H and the padding size P in the width direction W, the size F of the convolution kernel is obtained through the above-mentioned step S22. The number of layers C of adding 0 around the image is the number of layers of adding 0 around the input image or feature map and is used to control the size of the output feature map, and is also obtained through the above-mentioned network construction. The step size S is the distance that the convolution kernel slides on the input image or feature map and is obtained through the above-mentioned calculation.

[0152] S37. The backpropagation unit obtains the loss function value according to the loss function calculation formula "L = max(0, m + y * (f(x) - b)), where L is the loss function value, m is a hyperparameter, y is the sample label (0 or 1), f(x) is the predicted value of the model, and b is the classification boundary", and performs backpropagation to optimize the performance of the network model.

[0153] Further explanation, in the loss function calculation formula "L = max(0, m + y * (f(x) - b))", when f(x) ≤ b, then L = m + y(f(x) - b); when f(x) > b, then L = 0. In machine learning or optimization problems, f(x) is an optimization target, b is a threshold, and m and y are parameters. When the target value f(x) is less than or equal to the threshold b, the value of L is equal to m + y(f(x) - b); when the target value f(x) is greater than the threshold b, the value of L is 0. Use the training set data to train the model, adjust the model parameters to minimize the loss function, so that the predicted value of the positive sample is greater than a certain threshold, and the predicted value of the negative sample is less than a certain threshold. Then, through the backpropagation calculation formula "dz[l] = da[l] * g[l]′(z[l])", the convolution output values dw[l] = dz[l] * a[l - 1], db[l] = dz[l], da[l - 1] = W[l]T * dz[l] are obtained. In the formula, da[l] is the input data, da[1] is the output data, and g[l]′ is the derivative of the activation function sigmoid. The backpropagation of the convolution layer passes the error term da[l]da[l] to the previous layer through the convolution operation, flips the convolution kernel and applies it to the error map, calculates the local gradient through the derivative of the activation function, and is realized through matrix operations. The input and the convolution kernel are deformed into matrices, and matrix multiplication is performed, that is, the numbers in the convolution window are pulled into a row to form a column vector, and matrix multiplication is performed. The backpropagation of the fully connected layer calculates the gradient of the weight and the gradient of the bias through the chain rule. For each node, the error term is passed to the node of the previous layer through the weight matrix, and the local gradient is calculated through the derivative of the activation function, and is realized through matrix operations. Multiply the error term by the output of the current layer and multiply by the input of the previous layer to update it in the direction of minimizing the loss function.

[0154] S40. The model evaluation module performs model verification and evaluation according to the trained model, and adjusts and optimizes the model according to the verification results to improve the performance and accuracy of the model, and transmits it to the parameter determination module;

[0155] Please refer to Figure 12 as shown below. Step S40 includes the following steps:

[0156] S41. The classification and marking unit divides and marks corresponding data sample categories according to the dishwashing quality exception categories for subsequent machine learning of the model and transmits them to the learning and training unit;

[0157] Further explanation: Data classification is performed according to various quality exceptions in dishwashing by the dishwasher: "There is an odor in the dishwasher" is category 1, "The dishwasher makes too much noise" is category 2, "The tableware is not washed clean" is category 3, "There are spots or films on the tableware" is category 4, "There is residual detergent on the surface of the tableware" is category 5, "There is residual water in the dishwasher" is category 6, "The dishwasher is prone to breakage" is category 7; When category 1 is the positive sample, the rest of the categories are negative samples, that is, the marked data is (1, 0, 0, 0, 0, 0, 0), when category 2 is the positive sample, the rest of the categories are negative samples, that is, the marked data is (0, 1, 0, 0, 0, 0, 0), when category 3 is the positive sample, the rest of the categories are negative samples, that is, the marked data is (0, 0, 1, 0, 0, 0, 0), when category 4 is the positive sample, the rest of the categories are negative samples, that is, the marked data is (0, 0, 0, 1, 0, 0, 0), when category 5 is the positive sample, the rest of the categories are negative samples, that is, the marked data is (0, 0, 0, 0, 1, 0, 0), when category 6 is the positive sample, the rest of the categories are negative samples, that is, the marked data is (0, 0, 0, 0, 0, 1, 0), when category 7 is the positive sample, the rest of the categories are negative samples, that is, the marked data is (0, 0, 0, 0, 0, 0, 1); The above 6 exception categories are relatively typical exception classifications of the dishwasher, including but not limited to the above 7 categories, and one or more of these categories can also be re-divided into more categories, and more refined and in-depth divisions can be made according to the actual production inspection results. The above classifications are not fixed, and the model is re-trained every time the category changes to meet the dishwashing quality requirements.

[0158] S42. The learning and training unit determines the training model according to the gradient descent data, and inputs the data in the training set into the model for simulation training under different environmental conditions to ensure the accuracy of model recognition and transmits it to the model evaluation unit;

[0159] Further explanation: By continuously adjusting the model parameters to minimize the loss function, the prediction accuracy of the model is improved to ensure that the model can accurately identify the adaptability of the dishwasher in different environments; the model is trained with the data set in the training set to fit the data analysis law, that is, various learning parameters such as the weights and biases of the model are determined; and the data set in the validation set is used to adjust the model parameters and hyperparameters during the model training process to optimize the model performance, avoid overfitting, select the model, but do not participate in the determination of the learning parameters, and select the model parameters and hyperparameters with smaller model errors; then, the data set in the test set is used to evaluate the generalization ability of the model on unknown data after the model training is completed, and it is used once after training to evaluate the effect of the final model, and it does not participate in the learning parameter process or the hyperparameter selection process.

[0160] S43. The model evaluation unit obtains the comprehensive evaluation score F according to the model evaluation score calculation formula "F = 2(Ac * Re) / (Ac + Re), where F is the evaluation score of the trained model, Ac is the precision rate, and Re is the recall rate", and transmits it to the processing center;

[0161] Further explanation: The Ac and Re are respectively calculated through "Ac = (T P +T N ) / (T P +F P +F N +T N ) and Re = T P / (T P +F N )", where T P is the number of true positive samples, F P is the number of actually false positive samples, F N is the number of false negative samples, and T N is the number of true negative samples; after the model training is completed, tests are carried out to verify the accuracy and reliability of the model, and problems existing in the model may be found during the test for optimization and adjustment; the evaluation score of the trained model, that is, the F value, is the harmonic mean of the precision rate and the recall rate, which can evaluate the performance of the classification model, and the value range is from 0 to 1, where 1 is the best performance and 0 is the worst performance. If the F value is higher, the prediction effect of the model is better, and vice versa. Therefore, if the F value is close to 1, it indicates that the model performs well in maintaining the balance between the precision rate and the recall rate; adjust the hyperparameters according to the performance of the model such as the learning rate and the regularization coefficient to optimize the model performance.

[0162] S44. The processing center compares the actual evaluation score of the model with the model evaluation score standard stored in the memory: if it meets the standard, it is the predetermined dishwasher control parameter; if it does not meet the standard, it is transmitted to the alarm and notifies to continue training until it meets the standard.

[0163] Further explanation: The test evaluation criteria for the dishwasher quality anomaly category recognition training model are best when greater than 0.8, and are specifically determined according to factors such as the pre-cleaning degree, detergent category, washing temperature and time settings, tableware placement method, dishwasher maintenance, water quality problems, and washing program selection; the dishwasher control parameters include the operating parameters of the dishwasher and its auxiliary equipment, dishwasher operating parameters, dishwashing process flow, etc. Among them, the operating parameters of the dishwasher and its auxiliary equipment include the setting of the water softener, the addition amount of dishwashing powder, the tableware placement method, the selection of the cleaning mode, and the soaking time, rinsing pressure, rinsing temperature, rinsing time, number and time of rinsing, disinfection temperature and time, drying time and temperature, etc.; the dishwasher operating parameters include power, voltage, current, size, operating time, etc.; the dishwashing process flow includes pre-washing and time, main washing and time, rinsing and time, drying and time. These process parameters are automatically matched and applied during operation by the trained model to avoid various quality anomalies.

[0164] S50. The parameter determination module conducts cleaning tests on different tableware according to the dishwashing control parameters predicted by the trained model to obtain the optimal dishwasher control parameters to ensure subsequent dishwashing quality and transmits them to the application control module;

[0165] Please refer to Figure 13 As shown, the step S50 includes the following steps:

[0166] S51. The cleaning power consumption unit obtains the dishwashing cleaning and drying power consumption according to the dishwashing power consumption calculation formula "E = P1*T1 + P2*T2, where E is the dishwashing power consumption (kWh), P1 and P2 are the powers (kW) of dishwashing cleaning and drying respectively, and T1 and T2 are the times (h) of dishwashing cleaning and drying respectively" for subsequent dishwashing power consumption calculation and transmits it to the cleaning water consumption unit;

[0167] Further explanation: The dishwashing power consumption E is the total amount of electrical energy consumed by the dishwasher during a complete dishwashing process (including cleaning and drying), which reflects the energy efficiency level of the dishwasher; the dishwashing cleaning power P1 is the power consumed by the dishwasher during the cleaning stage, and its magnitude directly affects the cleaning effect and cleaning time. If the power is larger, the cleaning speed is faster, but the energy consumption also increases; the dishwashing drying power P2 is the power consumed by the dishwasher during the drying stage, and its magnitude determines the drying speed and drying effect. If the drying power is larger, the drying speed is faster, but the energy consumption also increases accordingly; the dishwashing cleaning time T1 is the time required for the dishwasher to complete the cleaning stage, which is determined by factors such as the design of the dishwasher, the selection of the cleaning program, and the degree of dirt on the tableware. If the cleaning time is shorter, the dishwashing efficiency is improved, but the cleaning effect is also affected; the dishwashing drying time T2 is the time required for the dishwasher to complete the drying stage, which is determined by factors such as the drying method, drying power, and the material and quantity of the tableware. If the drying time is shorter, the waiting time of the user is saved, and the user experience is improved; the powers P1 and P2 of dishwashing cleaning and drying and the times T1 and T2 of dishwashing cleaning and drying are respectively obtained by sensor detection.

[0168] S52. The cleaning water consumption unit obtains the dishwashing cleaning water consumption according to the dishwashing water consumption calculation formula "W = πR 2 *υ*T1, where W is the dishwashing water consumption (m 3 ), R is the radius of the dishwasher's water spray nozzle (m), υ is the water spray flow rate of the dishwasher (m / s), and T1 is the dishwashing cleaning time (s)" for subsequent dishwashing water consumption calculation and transmits it to the trial debugging unit;

[0169] Further explanation: The dishwashing water consumption calculation formula "W = πR 2 *υ*T1" is obtained by substituting "Q = πR 2 *υ" into "W = Q*T1". In the formula, Q is the water flow rate during dishwashing (m 3 / s). Since the water consumption of the dishwasher is determined by factors such as the model of the dishwasher, the selection of the washing program, and the quantity and degree of dirt on the tableware; the radius R of the dishwasher's water spray nozzle is obtained through design parameters, and the actual unit is cm. In order to unify the units in the dishwashing water consumption calculation formula, its unit is converted to m; the water spray flow rate υ of the dishwasher and the dishwashing cleaning time T1 are both obtained by sensor detection. Among them, the unit of the detected dishwashing cleaning time T1 is h, and in order to unify the units in the dishwashing water consumption calculation formula, its unit is converted to s; since the water spray flow rate υ of the dishwasher is related to water flow conditions such as water source pressure, pipeline length, and pipeline resistance, as well as other factors such as pipeline material and water flow resistance, it is necessary to select the material of the dishwasher's water spray pipe and reasonable water spray pipe design parameters to ensure the accuracy of the calculation results.

[0170] S54. The trial debugging unit conducts cleaning tests on different tableware through the dishwasher according to the predetermined dishwashing control parameters, detects and obtains the quality information of the cleaning to ensure the accuracy of the dishwashing quality, and transmits it to the processing center;

[0171] Furthermore, according to the control command and operation parameters, the tableware in the box filled with tableware to be washed is smoothly and orderly poured onto the conveyor belt of the dishwasher through the automatic unloading device; when the tableware enters the dishwasher, larger food residues on the tableware are removed by tools such as rotary brushes and scrapers, which helps to avoid large pieces of food interfering with the washing effect in subsequent cleaning and prevent it from contaminating the cleaning liquid; according to the control, the tableware is placed in the soaking tank and an appropriate amount of detergent and hot water are added for soaking according to the predetermined time to soften the oil stains and stubborn stains; high-temperature and high-pressure water flows are sprayed through the nozzles arranged at the top, bottom and sides inside the dishwasher, so that the combination of the detergent and the high-temperature hot water can more effectively remove the oil stains and food residues and rinse the surface of the tableware from different angles; after cleaning, the dishwasher rinses the tableware with clean water multiple times to remove the residual detergent on the tableware to ensure that the detergent on the surface of the tableware is completely removed and avoid the harm caused by the residual detergent to human health; after rinsing, common bacteria and viruses are killed by means of high-temperature disinfection or ultraviolet disinfection; after disinfection, drying technologies such as hot air drying or moisture absorption drying are adopted or the residual heat drying method is used to utilize the residual heat after washing for drying to ensure that the tableware is dry without water stains; after drying, the surface of the tableware is detected to ensure that the hygiene of the tableware surface meets the dishwashing quality standard.

[0172] S55. The processing center compares the dishwasher quality information with the dishwasher dishwashing quality standard stored in the memory: if it meets the standard, it is set as the formal dishwashing control parameter; if it does not meet the standard, it is transmitted to the alarm and the parameter adjustment and rework are notified.

[0173] It is further explained that the dishwashing control parameters also include washing programs: 1) Smart washing (also called AI smart washing, universal smart washing), which can automatically analyze the dirt on the dishes and select the best washing mode, saving time and effort, and is suitable for users who do not know how to choose programs, as well as situations where the number and degree of dirtiness of dishes are different; 2) Pre-wash / pre-rinse, with a running time of 10-20 minutes, only rinse the dishes with water to remove most of the food residues; 3) Super clean washing (also called strong washing), with strong washing force and long time, which can effectively remove heavy oil stains and sticky and dry food residues. Suitable for washing dishes after hot pot and beef hot pot, as well as heavily oily dishes such as woks and frying pans; 4) Daily washing (also called standard washing / ordinary washing), with moderate washing time and temperature, suitable for three meals a day for an average family, suitable for washing dishes with moderate oil stains or slightly dried food residues, with a running time of 1.5-2.5 hours, suitable for daily washing, ensuring full cleaning and drying; 5) Crystal soft washing, with a lower washing temperature, suitable for temperature-sensitive plastics, glass and easily damaged dishes, suitable for cleaning lightly oily dishes without stubborn stains 6) Quick wash (also called super-fast wash), with short washing time and slightly weaker decontamination ability, is suitable for situations where there are fewer dishes and the degree of dirtiness is low, such as breakfast, afternoon tea, supper, etc., when there are fewer dishes or when dishes are needed urgently. The running time is 30-60 minutes, which is suitable for slightly dirty dishes. The time is shorter but the effect may not be as good as standard washing; 7) Energy-saving wash (also called economic wash), with a cleaning effect similar to standard wash, but more energy-saving and water-saving, and a long washing time. It is suitable for use at night or when there is plenty of time, especially in the evening. For users who have more free time after meals, the running time is 2-3 hours. The cleaning time is long but the water and energy consumption are low, which is suitable for energy-saving needs; 8) Micro-steam washing (also called heavy cleaning), with a running time of 2-3 hours, is suitable for cleaning heavily oily tableware such as pots and pans. It can sterilize efficiently to ensure that dirt is completely removed; 9) Glassware washing, with a running time of about 1-1.5 hours, is suitable for cleaning fragile glassware and delicate ceramics; 10) Disinfection washing, with a running time of 2-3 hours, high-temperature disinfection is performed to ensure the killing of bacteria and germs.

[0174] S56. The abnormality recognition unit matches the real-time acquired dishwasher operation image with the corresponding image in the trained convolutional neural network model and confirms its abnormality category to facilitate subsequent dishwashing process improvement and parameter adjustment.

[0175] Further explanation: Input the image into the model. Use the trained model to predict the new monitoring image. According to the output result, judge the abnormal type of the dishwasher. If the model's judgment of the dishwasher abnormality reaches a certain threshold, trigger the warning system and take corresponding solutions in time; the abnormal types of the quality of the dishwasher's dishwashing include: 1) There is an odor in the dishwasher: Long-term use of the low-temperature washing process will cause an odor. Run the high-temperature washing process once a month to prevent the generation of odor; 2) The dishwasher makes too much noise: Collision noise is caused by improper installation of the spray arm or loose parts, motor failure or unreasonable design, the presence of foreign objects, etc., or noise is caused by pump failure, or vibration and noise are generated due to improper placement of tableware in the dishwasher. Check and adjust the installation position of the spray arm and remove obstacles, regularly check and repair the pump to ensure that the tableware is placed firmly and avoid mutual collision; 3) The tableware is not washed clean: It is difficult for the dishwasher to thoroughly remove heavy oil stains or dried food residues due to the non-rotation of the spray wall, incorrect loading of tableware, incorrect or improper use of detergent, the spray wall being blocked by bowls and plates, insufficient pre-treatment of tableware, blocked spray pipe, water quality problems, too low temperature setting, too short cleaning time, dirty inside the dishwasher, power supply or motor failure, tableware material or type, etc. Check and clean the spray wall and filter screen to ensure that the spray wall can rotate normally and the filter screen is not blocked; Load the tableware correctly, avoid overlapping of tableware or blocking the spray wall, and place the bowls and dishes with the mouths facing down; Adjust the dosage of the washing agent and determine the appropriate dosage according to the water quality hardness; 4) There are spots or films on the tableware: It is caused by the leakage of salt in the water softener or the empty salt box, too high temperature and too much detergent, using a three-in-one multi-functional detergent and not canceling the automatic adjustment function, etc. Use appropriate detergent and program, avoid using too much detergent or choosing an inappropriate cleaning mode; 5) Residual cleaner on the surface of the tableware: It is caused by the failure of the detergent dispenser, insufficient rinsing or incomplete cleaning inside the dishwasher, etc. Regularly check the detergent dispenser and clean the inside of the dishwasher; 6) There is water residue in the dishwasher: It is caused by a blocked drain pipe, blocked filter screen or residue in the drain pump. Regularly clean the drain pipe and drain pump to ensure unobstructed drainage; 7) The dishwasher is prone to breakage: Due to poor quality of raw materials and inadequate manufacturing process, the structural stability is poor, and problems such as component failure and water leakage are likely to occur, thus shortening the service life. Use high-quality raw materials and ensure reasonable manufacturing process to ensure the quality of the dishwasher.

[0176] S60. The application control module controls the dishwasher for dishwashing according to the set dishwashing control parameters and program instructions, and conducts various quality inspections to ensure that the dishwasher meets the quality requirements after automatic dishwashing.

[0177] Please refer to Figure 14 As shown, the step S60 includes the following steps:

[0178] S61. The category acquisition unit obtains the material and oil stain degree of the tableware to be cleaned through a high-definition camera, combines the washing requirements with the model to match the corresponding washing program, which can save energy and be environmentally friendly on the premise of ensuring clean washing, and transmits it to the slag removal and soaking unit;

[0179] Further explanation: There is enough space between the tableware to be cleaned to be placed in the automatic tipping device, so that hot air can circulate fully, improving the drying effect. At the same time, it avoids the tableware blocking the air outlet, ensuring that the hot air can smoothly blow onto each piece of tableware; during the placement process, the high-definition camera obtains the image of the tableware to be cleaned and converts it into recognizable tableware information. The number of tableware to be cleaned can also be obtained through a counting sensor and automatically input into the system model to match the corresponding dishwashing control parameters and washing programs to meet the requirements of maximizing energy conservation and environmental protection, and refer to the calculation results of the above steps S51 - S52 as the subsequent dishwashing control parameters; the dishwashing programs corresponding to different tableware in the model include: 1) Tableware with heavy oil stains, covered with heavy oil and dirt, or having stubborn dried oil stains, such as tableware after hot pot, wok, frying pan and other kitchen utensils. The corresponding washing programs are super clean wash, strong wash, etc., which can thoroughly clean stubborn stains and ensure that the tableware looks brand new; 2) Moderately soiled tableware, with a moderate degree of soiling, generally the bowls and dishes used in daily three meals, having slight food residues and oil stains. The corresponding washing programs are daily wash, standard wash, etc., which are suitable for the daily washing needs of most families and can meet the cleaning requirements of moderately soiled tableware; 3) Slightly soiled or oil-free tableware, generally slightly soiled or almost without oil stains, such as dessert tableware for afternoon tea. The corresponding washing programs are instant wash, quick wash, etc., with a short washing time and moderate decontamination ability, suitable for the situation of fewer tableware and a low degree of soiling; 4) Tableware made of special materials, including glassware, porcelain, some plastic tableware (requiring high temperature resistance), etc. The corresponding washing programs are crystal soft wash, glass wash, etc., using a lower washing temperature and a special water flow design, suitable for tableware sensitive to temperature, avoiding damage to the tableware or affecting its appearance; through the above trained model, the washing program is automatically selected based on the actual soiling degree and material of the tableware to ensure the washing effect and the integrity of the tableware.

[0180] S62. The slag removal and soaking unit removes larger food residues on the tableware through a rotary brush or a scraper according to the control command and predetermined operation parameters, flushes with high pressure water, and then puts it into the soaking tank for soaking to soften the oil stains and stubborn stains, and transmits it to the spray rinsing unit;

[0181] Further explanation: Before slag removal, the tableware in the box filled with tableware to be washed is smoothly and orderly poured onto the conveyor belt of the dishwasher through the automatic box tipping device according to the control command and operation parameters; when the tableware enters the dishwasher, larger food residues on the tableware are removed by tools such as rotary brushes and scrapers, which helps to avoid large pieces of food interfering with the washing effect in subsequent cleaning and preventing it from contaminating the cleaning liquid; then, the surface of the tableware is impacted by a predetermined high-pressure water flow to wash away larger food residues such as rice grains and vegetable leaves, so as to remove most of the obvious solid residues and prepare for subsequent cleaning; the water after spraying will flow into the filter system with the residues, and the filter will filter out residues of different sizes according to different pore sizes to prevent them from entering the subsequent cleaning link, so as to avoid blocking the pipeline and nozzle, ensuring the cleanliness of the tableware before entering the cleaning stage and laying a solid foundation for subsequent cleaning and disinfection work; after pre-washing, the tableware is placed in a soaking tank containing a predetermined detergent and hot water, and the tableware is soaked for a predetermined time to soften the oil stains and stubborn stains. The detergent helps to decompose the oil stains, while the hot water can accelerate the softening of the oil stains, making the stubborn stains easier to clean, effectively pre-treating the oil stains and stains on the tableware and laying a solid foundation for subsequent high-pressure spray cleaning, making the cleaning process more efficient and thorough.

[0182] S63. The spray rinsing unit sprays high-temperature and high-pressure water flow through the nozzles and rinses multiple times according to the control command and predetermined operation parameters to remove the surface oil stains and residual detergent, avoid harm to human health, and transfer it to the disinfection and drying unit;

[0183] Further explanation: After soaking, according to the control command, high-temperature water within the range of 55 - 70°C, water flow pressure, and frequency are set through the spray nozzles on the top, bottom, and sides inside the dishwasher to generate a periodic high-pressure pulsed water flow. This enables the combination of the predetermined detergent and high-temperature hot water to more effectively loosen and remove oil stains and food residues, and spray and clean the tableware from all angles. For tableware with grooves, gaps, or complex shapes, it can ensure that the water flow penetrates into them to effectively remove oil stains and food residues, thereby ensuring the cleanliness of the tableware. The water in the cleaning tank is continuously pumped and pressurized through the spray pipe by the internal circulation pump and re-sprayed to form a closed water flow circulation system. The water flow continuously flushes the tableware and the inside of the dishwasher, taking away the newly generated residues in a timely manner. At the same time, it can also evenly distribute the detergent in the water, improving the cleaning and slag removal effects, thus ensuring that the tableware is comprehensively and thoroughly cleaned. After spraying, cold water rinsing is carried out according to the predetermined temperature and time to further remove the detergent residues on the tableware, ensuring that the detergent is effectively rinsed off and avoiding the impact of residues on human health. After cold water rinsing, hot water rinsing is carried out according to the predetermined temperature and time, which can more thoroughly remove the residues on the tableware. At the same time, using high temperature can achieve a certain sterilization effect, ensuring that the tableware is cleaner and more hygienic. Rinsing is carried out a predetermined number of times until the residual detergent on the tableware is removed, ensuring that the detergent on the surface of the tableware is completely removed and avoiding the harm caused by the residual detergent to human health. Through the combination of cold water rinsing and hot water rinsing, it can ensure that there is no detergent residue on the tableware after cleaning and that a certain hygiene standard is achieved.

[0184] S64. After rinsing, the disinfection and drying unit kills surface bacteria and viruses through multiple disinfections according to the control command and predetermined operation parameters, and uses hot air drying to remove the surface water stains, ensuring that the tableware is dry without water stains and is transferred to the appearance detection unit;

[0185] Further explanation: After rinsing, most bacteria, viruses, spores and other microorganisms are effectively killed by disinfecting at a high temperature of 80 - 100 °C for 1 - 3 minutes according to the control command and predetermined operating parameters, ensuring the hygienic safety of tableware; then the DNA structure of microorganisms is damaged by ultraviolet irradiation through an ultraviolet disinfection device, making them lose their activity and further improving the disinfection effect; ozone with strong oxidizing property is generated by a special ozone generator, which can quickly kill bacteria and viruses to achieve the purpose of thorough disinfection, ensuring the hygienic safety of tableware after cleaning and meeting relevant hygienic standards; after disinfection, predetermined consumables such as rinse aid and dishwashing salt are added according to the control command and predetermined drying mode (including strong drying, energy-saving drying, silent drying, etc.). The rinse aid reduces the surface tension of water to prevent water droplets from remaining, and the dishwashing salt is used to increase the drying temperature to accelerate the drying speed of tableware and further improve the drying effect. Then the drying program is started to automatically dry the placed tableware, and the moisture on the surface of the tableware is quickly evaporated by a hot air blower or infrared heating, etc., keeping the tableware in a dry state to ensure that the tableware is dry without water stains.

[0186] S65. The appearance detection unit obtains the appearance information and odor information on the surface of the tableware after washing through the set high-definition camera and odor sensor respectively, to ensure that the hygiene of the tableware surface meets the dishwashing quality standard and transmits them to the hygiene detection unit;

[0187] Further explanation: According to the control command and set process parameters, the high-definition camera is controlled to take 360-degree angle shots, and images of different position points of the washed tableware are taken from multiple different angles to identify different position points of the washed tableware from different angles, so as to more accurately and comprehensively identify and obtain the position points and their shapes of the washed tableware. Or based on the images of the washed tableware taken from different angles, the washed tableware is identified by multi-angle matching, and then it is determined whether there are no food residues, oil stains, tea stains and other stains remaining on all parts of the tableware surface, whether there are no abnormal odors such as the smell of food residues and the smell of cleaning agents on the tableware, and whether the tableware is completely dry without moisture residue; and the odor information such as whether there are the smell of food residues and the smell of cleaning agents on the surface of the tableware is obtained through the set odor sensor; the images of the washed tableware include: 1) real-time images during the dishwashing process, which can monitor the running state during the dishwashing process and promptly discover and handle abnormal situations; 2) images of the tableware surface after washing, to conduct quality inspection on the dishwashing effect to check whether there are no stain residues and no moisture residues, etc.; 3) raw material images, to ensure that the quality of various raw materials such as cleaning agents meets the dishwashing quality requirements, avoid dishwashing abnormalities caused by raw material problems, and the situation of whether the tableware is neatly placed; according to specific dishwashing requirements and algorithm requirements, other types of image data such as images under different lighting conditions and images at different angles also need to be collected to improve the accuracy and robustness of the algorithm.

[0188] S66. The hygiene detection unit detects the hygiene index data of the surface of tableware after washing, such as the hygiene index, cleaning index, and drying index, through a tableware detector to ensure that the quality of the dishwasher meets the requirements and transmits it to the processing center;

[0189] Further explanation, according to the control command, the calibrated tableware detector program is set according to parameters such as the predetermined detection range, detection cycle, and working mode, and a clean swab or special sampling tool is evenly smeared on the surface of the tableware to be detected to obtain a tableware surface sample with an area of 10×10 cm. Then, the sampled swab is inserted back into the sleeve and processed by bending the valve, squeezing the swab head, etc., to ensure that the sample liquid in the swab head is fully extruded for detection; then the processed swab is inserted into the sample chamber of the tableware detector or the corresponding position, the instrument lid is covered, and the "Detection" button on the instrument is clicked or the detection is started according to the prompt operation to obtain the detection results, including whether the total number of bacteria does not exceed 5 Cfu / m 3 , whether there is no coliform group, whether there is no other pathogenic bacteria such as Staphylococcus aureus and Salmonella, whether the cleaning index reaches above 1.12, and whether the drying index reaches the A+ standard above 1.08. It can comprehensively detect the bactericidal situation on the surface of the tableware after being washed by the dishwasher, so as to accurately evaluate the cleaning effect and disinfection ability of the dishwasher, ensure the accurate and effective evaluation of the cleanliness of the tableware, provide an important guarantee for catering services and household hygiene, and thus ensure the cleanliness and hygiene standards of the tableware.

[0190] S67. The processing center compares the quality information of the dishwasher with the dishwasher washing quality standards stored in the memory: if it meets the standard, it notifies that the washing is completed; if it does not meet the standard, it transmits it to the alarm and notifies rework or repair.

[0191] Further explanation, the dishwasher washing quality standards include: 1) Appearance cleanliness: There is no residue of food residues, oil stains, tea stains and other stains on all parts of the tableware surface, there is no strange smell such as the smell of food residues and the smell of cleaning agents on the tableware, and the tableware is thoroughly dried and there is no water residue; 2) Hygiene index: The total number of bacteria on the tableware does not exceed 5 Cfu / m 3 , to ensure that it meets the relevant national hygiene standards, there is no coliform group, and there is no other pathogenic bacteria such as Staphylococcus aureus and Salmonella, to ensure the health and safety of users. 3) Performance index: The cleaning index of the tableware surface reaches the A+ standard above 1.12 and the drying index reaches above 1.08; the dishwasher can automatically control parameters such as washing temperature, washing time, water pressure, weighing powder or block, water intake, temperature, soft water, and rinse aid, so as to control the washing effect and make the hygiene index of the tableware surface meet the requirements after washing.

[0192] Further explanation: The above steps are displayed in sequence according to the arrows, but these steps do not necessarily need to be executed in the order indicated by the arrows. Unless clearly stated in this document, there is no strict order restriction for the execution of these steps. These steps can also be executed according to other orders. Moreover, some steps can include multiple sub-steps or multiple stages. These sub-steps or stages do not necessarily need to be completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential either, but can be executed alternately or in rotation with at least a part of other steps or sub-steps or stages of other steps.

[0193] Further explanation: The present invention is described in accordance with the content implemented by the software program of a dishwasher control system based on AI technology as described above. For each automatic control method of a dishwasher based on AI technology, it is divided into several modules or units to implement the software program instructions generated by each step. The software program instructions include the above-mentioned automatic control method of a dishwasher based on AI technology.

[0194] A dishwasher control system based on AI technology provided by the present invention further includes a computer-readable storage medium containing a memory; the memory stores a computer program, and when each functional module executes the computer program, it realizes the steps of an automatic control method of a dishwasher based on AI technology as described in any one of the above; a computer program is stored on the computer-readable storage medium, and when the computer program is executed by each functional module, it realizes the steps of an automatic control method of a dishwasher based on AI technology as described in any one of the above; it further includes a dishwasher control device based on AI technology, which is implemented by using the above-mentioned automatic control method of a dishwasher based on AI technology.

[0195] Further explanation: The computer-readable storage medium includes a memory, which can be used to store non-volatile software programs, non-volatile computer-executable programs, and modules, such as the programs and instructions corresponding to an automatic control method of a dishwasher based on AI technology in the present invention, including the information transfer instructions of each module; the memory executes various functional applications and data processing of each module by running the stored non-volatile software programs and instructions, that is, it realizes an automatic control method of a dishwasher based on AI technology in the above process embodiments; one or more units are stored in the memory, and when executed by the one or more modules, they execute an automatic control method of a dishwasher based on AI technology in any of the above process embodiments; the computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are executed by one or more modules, it can also be an automatic control method of a dishwasher based on AI technology in any of the above process embodiments.

[0196] Further explanation: The computer-readable medium can be a computer-readable signal medium, a computer-readable storage medium, or any combination of the two. It can be any tangible medium that contains or stores a program, and this program can be used by or in conjunction with an instruction execution system, device, or apparatus. This includes, but is not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. Among them, the computer-readable signal medium can include a data signal propagated in a baseband or as part of a carrier wave, carrying computer-readable program code. The propagated data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. It can also be any computer-readable medium other than a computer-readable storage medium. This computer-readable signal medium can send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, device, or apparatus. The program code it contains can be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0197] Further explanation: The computer program is divided into multiple modules / units, and the multiple modules / units are stored in the memory and executed by each of the modules / units to complete the present invention; the multiple modules / units can be a series of computer program instructions that can complete specific functions, and these instructions are used to describe the execution process of the computer program in each of the modules / units.

[0198] Further explanation: The content described above in the present invention is written with reference to some of the content implemented in the software copyrights such as "Dishwasher Intelligent Control System (Registration Number: 2021SR0563764)" successively applied by our company starting from April 2021.

[0199] The present invention also provides a dishwasher based on AI technology, which is implemented by using the above-described automatic control method for a dishwasher based on AI technology.

[0200] Further explanation: The control device is composed of the above-related detection equipment or devices. According to the needs of dishwasher manufacturing enterprises, it can be made into a complete set of automatic production detection equipment for dishwashers together with the dishwasher production detection equipment; it can also be made into unit devices of each functional module belonging to each step or the entire control device. When installed, wireless connection is used to connect each control device to each dishwasher production detection equipment; the structures of these devices are not described in detail here; this invention application is not only applicable to professional dishwashing factories, but also applicable to the catering industries such as hotels and guesthouses, and is also applicable to household dishwashing, which can improve the dishwashing efficiency.

[0201] For those skilled in the art, it is obvious that this application is not limited to the details of the above exemplary embodiments, and without departing from the spirit or basic characteristics of this application, this application can be implemented in other specific forms. Therefore, from any point of view, the embodiments should be regarded as exemplary and non-limiting. The scope of this application is defined by the appended claims rather than the above description. Therefore, it is intended to cover all changes within the meaning and scope of the equivalent elements of the claims in this application.

[0202] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application and not to limit them. Although this application has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of this application can be modified or equivalently replaced, and all should be included in the protection scope of this application.

Claims

1. A dishwasher automatic control method based on AI technology, characterized in that: The method is applied to a dishwasher control system based on AI technology, the system comprising an information acquisition module, a model construction module, a model training module, a model evaluation module, a parameter determination module, an application control module, a wireless communication module, a memory, an alarm, a processing center, and an intelligent mobile terminal; the information acquisition module, the model construction module, the model training module, the model evaluation module, the parameter determination module, the application control module, the wireless communication module, the memory, and the alarm are respectively connected to the processing center; the intelligent mobile terminal is respectively connected to the wireless communication module wireless network within the range of a wireless network or the Internet; the method comprises the following steps: S10, before application, the information acquisition module obtains normal and abnormal historical image data of dishwasher production and pre-processes it for subsequent model construction, and passes it to the model construction module; S20, the model building module determines the model architecture, designs the network hierarchy, adds auxiliary layers, defines model parameters, and builds the model based on the extracted feature information, so as to facilitate subsequent model training and verification, and passes it to the model training module, including the following steps: S21, the network level unit uses the selected convolutional neural network as the model architecture and customizes and optimizes the network level structure according to the specific application scenarios and requirements for subsequent defect detection and quality identification, and passes it to the network parameter unit; S22, the network parameter unit adjusts the number of network layers, convolution kernel size, step size, padding method and selects the loss function and optimization algorithm according to the network hierarchy structure to ensure the performance and accuracy of the model, and passes it to the hierarchical optimization unit; S23, the hierarchical optimization unit adjusts the size and normalization of the input data by adding a zero padding layer and a normalization layer before and after the convolution layer to improve the model training speed and stability, and passes it to the data partitioning unit; S24, the data division unit divides the data set with key feature vectors after extraction into a training set, a validation set and a test set and establishes a convolutional neural network structure for subsequent model training; S30, the model training module trains the model according to the collected data and adjusts the model parameters to optimize the model performance to predetermine the dishwasher control parameters, ensure the stability of the dishwasher operation quality, and pass it to the model evaluation module; S40, the model evaluation module performs model verification and evaluation based on the trained model, and adjusts and optimizes the model based on the verification results to improve the performance and accuracy of the model, and passes it to the parameter determination module, including the following steps: S41, the classification and labeling unit classifies the data samples into corresponding categories according to the abnormal dishwashing quality categories and labels them for subsequent machine learning of the model, and transmits them to the learning and training unit; S42, the learning training unit determines the training model according to the gradient descent data, and inputs the data in the training set into the model for simulation training under different environmental conditions to ensure the accuracy of model recognition, and transmits it to the model evaluation unit; S43, the model evaluation unit obtains the comprehensive evaluation score F according to the model evaluation score calculation formula "F = 2 (Ac * Re) / (Ac + Re), F is the training model evaluation score, Ac is the precision, Re is the recall rate", and transmits it to the processing center; S44, the processing center compares the actual evaluation score of the model with the evaluation score standard of the model stored in the memory: if it meets the standard, it is the predetermined dishwasher control parameter; if it does not meet the standard, it is transmitted to the alarm and notified to continue training; S50, the parameter determination module performs washing tests on different tableware according to the dishwashing control parameters predicted by the trained model to obtain the best dishwasher control parameters to ensure the subsequent dishwashing quality, and transmits them to the application control module; S60: The application control module controls the dishwasher to wash dishes according to the set dishwashing control parameters and program instructions and performs various quality tests to ensure that the dishwasher meets the quality requirements after automatically washing dishes.

2. The automatic control method for a dishwasher based on AI technology according to claim 1, characterized in that : The system further comprises: the wireless communication module is provided with a wireless network unit, which is responsible for sending and receiving wireless signals and automatically networking with the intelligent mobile terminal within an effective network range; The alarm compares the actual evaluation score of the model with the evaluation score standard of the model stored in the memory, and automatically sounds an alarm and notifies to continue training if the standard is not met; and compares the dishwasher quality information with the dishwasher dishwashing quality standard stored in the memory, and automatically sounds an alarm and notifies to adjust parameters for rework; and compares the dishwasher quality information with the dishwasher dishwashing quality standard stored in the memory, and automatically sounds an alarm and notifies to rework or repair if the standard is not met; The memory is responsible for storing information of the information acquisition module, the model construction module, the model training module, the model evaluation module, the parameter determination module, the application control module, the wireless communication module, and the alarm, as well as the model evaluation sub-standard and the dishwasher dishwashing quality standard; The processing center is responsible for information transmission among the functional modules, alarms, and memories, and is the hub of the system. The processing center compares the actual evaluation score of the model with the evaluation score standard of the model stored in the memory: if the standard is met, it is the predetermined dishwasher control parameter; if not, it is transmitted to the alarm and notified to continue training; and compares the dishwasher quality information with the dishwasher dishwashing quality standard stored in the memory: if the standard is met, it is set as the official dishwashing control parameter; if not, it is transmitted to the alarm and notified to adjust the parameters for rework; and compares the dishwasher quality information with the dishwasher dishwashing quality standard stored in the memory: if the standard is met, it is notified that the dishwashing is completed; if not, it is transmitted to the alarm and notified to rework or repair; The information acquisition module includes a data acquisition unit, a cleaning data unit, an enhancement data unit, an integration data unit, a conversion data unit, a filtering and denoising unit, a grayscale conversion unit, and a feature extraction unit, which is responsible for acquiring normal and abnormal historical image data of dishwasher production and preprocessing it, and passing it to the model building module; The model building module includes a network level unit, a network parameter unit, a hierarchical optimization unit, and a data partitioning unit, which are responsible for determining the model architecture, designing the network level structure, adding auxiliary layers, defining model parameters, and building the model according to the extracted feature information, and passing them to the model training module; The model training module includes an input filling unit, a convolution input unit, a pooling conversion unit, a fully connected layer unit, a normalized output unit, an output conversion unit, and a back propagation unit, which is responsible for training the model according to the collected data and adjusting the model parameters to optimize the model performance to predetermine the dishwasher control parameters and pass them to the model evaluation module; The model evaluation module includes a classification labeling unit, a learning training unit, and a model evaluation unit, which is responsible for model verification and evaluation based on the trained model, and adjusting and optimizing the model based on the verification results, and passing it to the parameter determination module; The parameter determination module includes a washing power consumption unit, a washing water consumption unit, a trial debugging unit, and an abnormality recognition unit, which is responsible for performing washing tests on different tableware according to the dishwashing control parameters predicted by the trained model to obtain the best dishwasher control parameters and pass them to the application control module; The application control module includes a category acquisition unit, a residue removal and soaking unit, a spray rinsing unit, a disinfection and drying unit, an appearance detection unit, and a hygiene detection unit, which is responsible for controlling the dishwasher to wash dishes and performing various quality tests according to set dishwashing control parameters and program instructions to ensure that the dishwasher meets the quality requirements after automatically washing dishes.

3. The automatic control method of a dishwasher based on AI technology according to claim 1, characterized in that: The step S10 comprises the following steps: S11, the data acquisition unit obtains historical data of the degree of dirtiness, quantity, type of cleaning effects and control parameters of similar dishwashers on different tableware by networking with the industry database, and transmits it to the cleaning data unit; S12, the cleaning data unit cleans the collected dishwashing history data to remove abnormal values, duplicate values ​​or missing values ​​in the data to improve the quality and accuracy of the data, and transmits it to the enhanced data unit; S13, the enhanced data unit increases the quantity and diversity of dishwashing training data through data enhancement methods such as rotation, scaling, flipping, cropping, and color transformation to improve the generalization ability of the model, and passes it to the integrated data unit; S14, the integrated data unit obtains the standardized dishwashing data according to the data standardization processing formula "z = (x-μ) / σ, z is the standardized data, x is the original data, μ is the mean of the data, σ is the standard deviation of the data" to improve the stability of the model, and passes it to the conversion data unit; S15, the conversion data unit obtains the normalized dishwashing data according to the normalization calculation formula "x'=(x-min(x)) / (max(x)-min(x)), x' is the normalized data, x is the original data, min(x) and max(x) are the minimum and maximum values ​​of the data respectively" to improve the model performance, and passes it to the filtering and denoising unit; S16, filtering and denoising unit is calculated according to the Gaussian filtering method" G(x,y) is the two-dimensional Gaussian function pixel, (x,y) is the pixel coordinate, and σ is the standard deviation” The denoised dishwashing image data is obtained for grayscale image conversion and passed to the grayscale conversion unit; S17, the grayscale conversion unit obtains the grayscale dishwashing image data according to the grayscale calculation formula "f(i,j) = max(R(i,j), G(i,j), B(i,j)), f(i,j) is the grayscale image, R(i,j), G(i,j), B(i,j) are the original images of three colors respectively", so as to extract the features later, and transmits it to the feature extraction unit; S18, the feature extraction unit converts the labeled data into feature vectors useful for model training and extracts key features of appearance cleanliness, dryness, and hygiene indicators to improve the training speed and performance of the model; The step S30 comprises the following steps: S31, input filling unit according to the data filling size calculation formula "P H =[(Ho-1)*S H +K H -H i ] / 2,P W =[(Wo-1)*S W +K W -Wi] / 2,P H , P W are the padding sizes in height / width directions, Hi and Wi are the height / width of the input feature map, and K H , K W are the height / width of the convolution kernel, S H , S W are the values ​​of the step length in the height / width direction, Ho and Wo are the height and width of the output feature map respectively. The padding data is obtained and input, and passed to the convolution input unit; S32, the convolution input unit obtains the convolution input value and activates the function input according to the convolution input calculation formula "z(t) = ∫x(m)y(tm)dm, z(t) is the output function, x(t) is the input function, y(t) is the convolution kernel function, and dm is the integral differential element of the variable m", and passes it to the pooling conversion unit; S33, the pooling conversion unit calculates the maximum pooling formula "Z(i,j)=max(X[i*P S (i+1)*P S ,j*P S (j+1)*P S ]), Z(i,j) is a pixel value in the output feature map after pooling, i and j are the positions in the output feature map, max is the maximum value of all pixel values ​​in the input window, X is the input feature map, P S The maximum pixel value after pooling is obtained by "window size of pooling operation" and enters the fully connected layer to retain important feature information and pass it to the fully connected layer unit; S34, the fully connected layer unit is calculated according to the fully connected layer formula "y=f(∑(w n *x n )+b), y is the output result, f is the activation function, w n is the weight of the nth input feature, x n is n input features, n is the dimension of the input features, and b is the bias. The output data of the connection layer is obtained and enters the output layer for subsequent output calculation and is passed to the normalized output unit. S35, the normalized output unit is calculated according to the Batch Norm layer formula "h=φ(B N (Wx+b)), h is the output of the fully connected layer, φ is the activation function, B N is the batch normalization operator, W is the weight parameter, x is the input of the fully connected layer, and b is the bias parameter. The output of Batch Norm is obtained and passed to the output conversion unit; S36, the output conversion unit obtains the output value size after convolution according to the output layer conversion calculation formula "N = (P-F + 2C) / S + 1, N is the output size after convolution, P is the input size before convolution, F is the convolution kernel size, C is the number of layers of 0 added around the image, and S is the step size" for subsequent model analysis and training, and passes it to the back propagation unit; S37, the back propagation unit obtains the loss function value according to the loss function calculation formula "L = max(0, m + y * (f (x) - b)), L is the loss function value, m is the hyperparameter, y is the sample label (0 or 1), f (x) is the predicted value of the model, and b is the classification boundary" and back propagates to optimize the performance of the network model; The step S50 comprises the following steps: S51, the washing power consumption unit obtains the washing and drying power consumption of the dishes according to the dishwashing power consumption calculation formula "E = P1*T1+P2*T2, E is the dishwashing power consumption (kWh), P1 and P2 are the power (kW) of washing and drying of the dishes, T1 and T2 are the time (h) of washing and drying of the dishes, so as to calculate the subsequent dishwashing power consumption, and transmits it to the washing water consumption unit; S52, the washing water consumption unit is calculated according to the dishwashing water consumption formula "W=πR 2 *υ*T1,W is the water consumption for washing dishes (m 3 ), R is the radius of the dishwasher water spray port (m), υ is the dishwasher water spray flow rate (m / s), T1 is the dishwashing cleaning time (s)” to obtain the dishwashing cleaning water consumption for subsequent dishwashing water consumption calculation and pass it to the trial debugging unit; S54, the trial debugging unit performs a cleaning test on different tableware through the dishwasher according to the predetermined dishwashing control parameters and detects and obtains cleaning quality information to ensure the accuracy of dishwashing quality, and transmits it to the processing center; S55, the processing center compares the dishwasher quality information with the dishwasher dishwashing quality standard stored in the memory: if it meets the standard, it is set as the official dishwashing control parameter; if it does not meet the standard, it is transmitted to the alarm and notified to adjust the parameters and rework. S56. The abnormality recognition unit matches the real-time acquired dishwasher operation image with the corresponding image in the trained convolutional neural network model and confirms its abnormality category to facilitate subsequent dishwashing process improvement and parameter adjustment.

4. The automatic control method for a dishwasher based on AI technology according to claim 1, characterized in that: The step S60 comprises the following steps: S61, the category acquisition unit obtains the material and oil pollution degree of the tableware to be washed through a high-definition camera and matches the corresponding washing program with the model in combination with the washing requirements, which can save energy and protect the environment while ensuring that the tableware is clean, and transmits it to the slag removal and soaking unit; S62, the residue removal and soaking unit removes larger food residues on the tableware by means of a rotating brush or a scraper according to the control command and the predetermined operation parameters, and then puts the tableware into a soaking tank after high-pressure water flushing to soften the oil and stubborn stains, and transfers the residues to the spray rinsing unit; S63, the spray rinsing unit sprays high-temperature and high-pressure water through the nozzle according to the control command and the predetermined operation parameters and rinses multiple times to remove surface oil and residual detergent to avoid harm to human health, and transfers it to the disinfection and drying unit; S64, after rinsing, the disinfection and drying unit kills surface bacteria and viruses through multiple disinfections according to the control command and the predetermined operation parameters, and uses hot air drying to remove surface water marks to ensure that the tableware is dry and free of water marks, and then passes it to the appearance inspection unit; S65, the appearance detection unit obtains the appearance information and odor information of the tableware surface after washing through the set high-definition camera and odor sensor, so as to ensure that the hygiene of the tableware surface meets the dishwashing quality standard, and transmits it to the hygiene detection unit; S66, the hygiene inspection unit detects the hygiene index, cleaning index, and drying index of the tableware surface after washing through the tableware inspection instrument to ensure that the quality of the dishwasher meets the requirements and transmits the data to the processing center; S67, the processing center compares the quality information of the dishwasher with the dishwasher dishwashing quality standard stored in the memory: if the standard is met, the dishwashing is notified to be completed; if the standard is not met, the alarm is transmitted and a rework or repair is notified.

5. The automatic control method for a dishwasher based on AI technology according to claims 1-4, characterized in that: The system also includes a computer-readable storage medium containing a memory; the memory stores a computer program, and when the functional modules execute the computer program, the steps of the dishwasher automatic control method based on AI technology described in any one of claims 1 to 4 are implemented; the computer-readable storage medium stores a computer program, and when the computer program is executed by the functional modules, the steps of the dishwasher automatic control method based on AI technology described in any one of claims 1 to 4 are implemented; and also includes a dishwasher control device based on AI technology, which is implemented by the dishwasher automatic control method based on AI technology described in any one of claims 1 to 4.

6. A dishwasher based on AI technology, characterized by: This is achieved by using an AI-based dishwasher automatic control method as described in any one of claims 1 to 4.

Images