Intelligent vegetable cleaning machine operation control system and method based on Internet of Things

Abstract

The invention discloses an intelligent vegetable cleaning machine operation control system and method based on the Internet of Things, and particularly relates to the field of mechanical engineering, and the system comprises a vegetable image collection module, a vegetable category judgment module, a sensor data collection module, a sensor data analysis module, a collaborative analysis module and a user feedback module. Image signals are converted into digital signals to be transmitted to the main control module, the system can monitor the cleaning process in real time and adjust the cleaning strategy in time, dynamic optimization of the cleaning process is guaranteed, and consistency and quality of the cleaning effect are improved; according to a vegetable judgment result, a vegetable category judgment module can send four different control signals to an automatic control unit so as to start a corresponding cleaning mode, so that the cleaning quality is effectively improved, meanwhile, the resource consumption is reduced, and perfect combination of intelligence and environmental protection is realized; and through real-time adjustment and optimization, user participation and product innovation are promoted, and the cleaning effect is improved.

Description

Technical Field

[0001] The present invention relates to the field of mechanical engineering technology, and more specifically, to an operation control system and method of an intelligent vegetable washing machine based on the Internet of Things. Background Art

[0002] With the rapid development of modern agriculture and food industry, food safety and hygiene standards have received increasing attention. In this context, the application of automation and intelligent technologies is particularly important. They not only improve production efficiency, but also significantly enhance food safety assurance capabilities, especially in the process of vegetable washing. Traditional manual washing methods can no longer meet the needs of large-scale production and high-standard cleaning. Therefore, the research and development of intelligent vegetable washing machines and their operation control systems have become a key direction of industry innovation.

[0003] The intelligent vegetable washing machine operation control system integrates advanced sensor technology, automatic control and Internet of Things technology to achieve precise control and efficient management of the washing process. This technological innovation has brought significant positive impacts to the fields of agriculture and food processing. First, it greatly improves the washing efficiency, shortens the time from the field to the table, and ensures the freshness of the ingredients. Secondly, through the precise ratio of chemical substances and water recycling, it reduces resource waste and promotes sustainable development. More importantly, the intelligent monitoring and adjustment mechanism ensures the consistency and safety of the washing quality, reduces the risk of food contamination, and enhances consumer confidence.

[0004] However, there are still some shortcomings in its actual use, such as the complexity of the system and the technical dependence, which requires operators to have certain professional skills, which to some extent hinders the rapid promotion of the technology. In addition, when dealing with certain vegetables with special shapes or fragile textures, the existing technology may still have problems of damage or incomplete cleaning, affecting the quality and market acceptance of the final product. Therefore, continuous R&D investment and technological innovation, especially in reducing costs, improving applicability and simplifying operating procedures, are crucial to promoting the application of intelligent vegetable washing machine operation control systems on a wider range. Summary of the invention

[0005] In order to overcome the above-mentioned defects of the prior art, the present invention provides an operation control system of an intelligent vegetable washing machine based on the Internet of Things, which solves the problems raised in the above-mentioned background technology through the following scheme.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] An operation control system of an intelligent vegetable washing machine based on the Internet of Things, comprising:

[0008] Vegetable image acquisition module: used to capture images of the vegetable washing area through a high-definition camera, pre-process the acquired images, convert the images from analog signals into digital signals and transmit them to the vegetable category judgment module;

[0009] Vegetable category judgment module: used to receive the image data of the vegetables to be cleaned in the vegetable image acquisition module, identify the category of the vegetables through the vegetable image discrimination model, and send the corresponding control signal to the sensor data analysis module;

[0010] Sensor data acquisition module: used to obtain relevant information of the environment in which the vegetables to be washed are located and energy consumption information of the washing machine through sensors, form a set of washing information of the vegetables to be washed and a set of energy consumption information of the washing machine, and transmit them to the sensor data analysis module;

[0011] Sensor data analysis module: used to analyze the cleaning information set of the vegetables to be cleaned and the energy consumption information set of the cleaning machine transmitted by the sensor data acquisition module, and combine the type of the vegetables to be cleaned determined by the vegetable category determination module to obtain the automatic adjustment value of the cleaning agent and the energy consumption value of the cleaning machine, and transmit them to the collaborative analysis module; including an automatic control unit, an energy consumption analysis unit, and a recipe database;

[0012] Collaborative analysis module: used to analyze the data information transmitted by the sensor data analysis module, build a collaborative analysis function model, and evaluate the cleaning effect of the vegetable washing machine;

[0013] User feedback module: used to obtain the terminal user's evaluation of the cleaning effect, determine the deviation of the cleaning effect using the collaborative analysis function value transmitted by the collaborative analysis module, and provide timely feedback on abnormal cleaning effects.

[0014] Preferably, the preprocessing step of the vegetable image acquisition module includes:

[0015] A1. Remove noise through filters and adjust brightness and contrast by adjusting pixel values ​​to improve image quality;

[0016] A2. Through computer vision technology, the characteristics of vegetables are extracted from the image, and the analog signal of the image is converted into a digital signal. The digital signal of the image is represented by the grayscale value of the pixel located in the x-th column and the grayscale value of the pixel in the y-th row in the image I, denoted as I(x, y), where x represents the width of the image, that is, the number of pixels in the horizontal direction of the image, and y represents the length of the image, that is, the number of pixels in the vertical direction of the image.

[0017] Preferably, the calculation model for vegetable image discrimination is specifically expressed as:

[0018]

[0019] Among them, P(l|I) represents the judgment result that vegetable image I belongs to vegetable category l, l represents the vegetable category of vegetable image I, I represents the image data preprocessed by the vegetable image acquisition module, S(l) represents the judgment function of vegetable category l, L represents the total number of all vegetable categories, l′ represents all possible vegetable categories except vegetable image I, and S(l′) represents the judgment function of vegetable category l′.

[0020] Preferably, the vegetable category judgment module sends an A signal and uses spray cleaning if the vegetable category is type A; sends a B signal and uses immersion cleaning if the vegetable category is type B; sends a C signal and uses steam cleaning if the vegetable category is type C; sends a D signal and uses bubble cleaning if the vegetable category is type D; Type A represents vegetables with rough or easily damaged surfaces; Type B represents harder root vegetables; Type C represents vegetables that require gentle disinfection or softening of the skin; Type D represents vegetables that require gentle removal of surface dirt while avoiding mechanical damage.

[0021] Preferably, the cleaning information set of the vegetables to be cleaned is recorded as {H, ph, T}, wherein H represents the humidity of the cleaning area, ph represents the pH value of the water quality parameter, and T represents the temperature of the cleaning water; the energy consumption information set of the cleaning machine is recorded as {EP(l|I), PP(l|I), CP(l|I)}, wherein E represents the power consumption value under the cleaning mode determined according to the vegetable image recognition result P(l|I), P represents the flushing pressure value under the cleaning mode determined according to the vegetable image recognition result P(l|I), and C represents the amount of water used to clean a unit weight of vegetables under the cleaning mode determined according to the vegetable image recognition result P(l|I).

[0022] Preferably, the calculation model of the automatic adjustment value of the cleaning agent is specifically expressed as:

[0023]

[0024] Among them, L represents the automatic adjustment value of the cleaning agent, and N represents the total number of times the cleaning is completed. represents the optimal concentration for the i-th cleaning calculated by the automatic adjustment unit, It is represented as the optimal concentration for the i-th cleaning in the formula database;

[0025] Furthermore, the calculation formula of the optimal concentration of the i-th cleaning method calculated by the automatic adjustment unit is specifically expressed as:

[0026] C opt =α1×σ(α2×σ(α1×[H, pH, T, P(l|I)]+b1)+b2)+b3,

[0027] Among them, α1, α2, and α3 represent the preset weights respectively, σ(x) represents the activation function of the automatic adjustment model, [H, ph, T, P(l|I)] represents the input vector of the automatic adjustment model, H represents the humidity of the cleaning area, ph represents the pH value of the water quality parameter, T represents the temperature of the cleaning water, and P(l|I) represents the vegetable image discrimination result.

[0028] Preferably, the calculation model of the energy consumption of the cleaning machine is specifically expressed as

[0029]

[0030] Where γ represents the energy consumption of the washing machine under the washing mode determined according to the vegetable image discrimination result P(l|I), k1 represents the efficiency factor of converting water consumption into energy, k2 represents the efficiency factor of converting pressure into energy, E e P(l|I) Expressed as the power consumption value in P(l|I) mode, C e P(l|I) It is expressed as the water consumption per unit weight of vegetables washed in the P(l|I) mode, P e P(l|I) It is expressed as the flushing pressure value under the P(l|I) mode, k3 is expressed as the efficiency factor of converting time into energy, and t is expressed as the cleaning time.

[0031] Preferably, the collaborative analysis function model is specifically expressed as:

[0032]

[0033] Among them, CAFV represents the collaborative analysis function value, L represents the automatic adjustment value of the cleaning agent, κ represents the influencing factor of data collection, M represents the total number of cleaning methods, γ j It is expressed as the energy consumption of the cleaning machine under the j-th cleaning mode, It is expressed as the energy consumption of the cleaning machine under the jth cleaning mode under ideal conditions.

[0034] Preferably, the steps for obtaining the terminal user's evaluation of the cleaning effect, determining the deviation of the cleaning effect using the collaborative analysis function value transmitted by the collaborative analysis module, and providing timely feedback on the abnormal cleaning effect include:

[0035] Pre-set user evaluation results, and set the user evaluation results as exceeding cleaning expectations, meeting cleaning expectations, and failing to meet cleaning expectations;

[0036] When the terminal user's evaluation of the cleaning effect is obtained as exceeding the cleaning expectation or failing to meet the cleaning expectation, the actual cleaning information set and actual cleaning operation parameters of the vegetables that have completed the cleaning operation are counted; based on the actual cleaning information set and actual cleaning operation parameters, the vegetable category judgment module and the sensor data analysis module are corrected.

[0037] The present invention also provides an operation control method of an intelligent vegetable washing machine based on the Internet of Things. The operation control system of the intelligent vegetable washing machine based on the Internet of Things comprises the following steps:

[0038] S1. Collecting vegetable images: Capturing images of the vegetable washing area through a high-definition camera, pre-processing the collected images, converting the images from analog signals into digital signals and transmitting them to the vegetable category judgment module;

[0039] S2, discriminating the vegetable category: receiving the image data of the vegetables to be cleaned in the vegetable image collection, discriminating the category of the vegetables through the vegetable image discrimination model, and sending the corresponding control signal to the data analysis;

[0040] S3, collecting sensor data: obtaining relevant information of the environment of the vegetables to be washed and energy consumption information of the washing machine through sensors, forming a set of washing information of the vegetables to be washed and a set of energy consumption information of the washing machine, and transmitting them to data analysis;

[0041] S4, analyzing sensor data: analyzing the cleaning information set of the vegetables to be cleaned and the energy consumption information set of the cleaning machine transmitted by the data acquisition, combining the vegetable identification with the type identification of the vegetables to be cleaned, obtaining the automatic adjustment value of the cleaning agent and the energy consumption value of the cleaning machine, and transmitting them to the collaborative analysis;

[0042] S5. Analyze the synergistic effect: Analyze the data information transmitted by the data analysis, build a synergistic analysis function model, and evaluate the cleaning effect of the vegetable washing machine;

[0043] S6. Obtain user feedback: Obtain the terminal user's evaluation of the cleaning effect, use the collaborative analysis function value transmitted by the collaborative analysis to determine the deviation of the cleaning effect, and provide feedback on abnormal cleaning effects in a timely manner.

[0044] Technical effects and advantages of the present invention:

[0045] 1. The present invention converts the image signal into a digital signal and transmits it to the main control module. The system can monitor the cleaning process in real time and adjust the cleaning strategy in time, thereby ensuring the dynamic optimization of the cleaning process and improving the consistency and quality of the cleaning effect.

[0046] 2. According to the vegetable identification results, the vegetable category identification module of the present invention will send four different control signals to the automatic control unit to start the corresponding cleaning mode, effectively improve the cleaning quality, reduce resource consumption, and achieve a perfect combination of intelligence and environmental protection;

[0047] 3. The present invention promotes user participation and product innovation and improves cleaning effects through real-time adjustment and optimization. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 It is a schematic diagram of the system structure of the present invention.

[0049] Figure 2 It is a structural schematic diagram of the sensor data analysis module in the present invention.

[0050] Figure 3 It is a schematic diagram of the method steps of the present invention. DETAILED DESCRIPTION

[0051] The following will be combined with the drawings in this embodiment of the present invention to clearly and completely describe the technical solution in this embodiment of the present invention. Obviously, the described embodiment is only a part of the embodiment of the present invention, not all of the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0052] As attached Figure 1 The shown operation control system of an intelligent vegetable washing machine based on the Internet of Things includes a vegetable image acquisition module, a vegetable category judgment module, a sensor data acquisition module, a sensor data analysis module, a collaborative analysis module and a user feedback module.

[0053] The vegetable image acquisition module is used to capture images of the vegetable cleaning area through a high-definition camera. After preprocessing the acquired images, the images are converted from analog signals to digital signals and transmitted to the vegetable category judgment module.

[0054] Furthermore, the preprocessing steps of the vegetable image acquisition module include:

[0055] A1. Remove noise through filters and adjust brightness and contrast by adjusting pixel values ​​to improve image quality;

[0056] A2. Through computer vision technology, the characteristics of vegetables are extracted from the image, and the analog signal of the image is converted into a digital signal. The digital signal of the image is represented by the grayscale value of the pixel located in the x-th column and the grayscale value of the pixel in the y-th row in the image I, denoted as I(x, y), where x represents the width of the image, that is, the number of pixels in the horizontal direction of the image, and y represents the length of the image, that is, the number of pixels in the vertical direction of the image.

[0057] In this embodiment, the vegetable image acquisition module captures the images of vegetables in the cleaning area and improves the image clarity through preprocessing, so that the system can accurately identify the surface condition of the vegetables and adjust the cleaning parameters in a targeted manner to ensure that each vegetable is properly cleaned without causing damage; the application of computer vision technology helps to classify and clean, screen out vegetables that are not suitable for cleaning, and improve overall processing efficiency; by converting image signals into digital signals and transmitting them to the main control module, the system can monitor the cleaning process in real time and adjust the cleaning strategy in a timely manner, thereby ensuring dynamic optimization of the cleaning process and improving the consistency and quality of the cleaning effect.

[0058] The vegetable category judgment module is used to receive the image data of the vegetables to be cleaned in the vegetable image acquisition module, identify the category of the vegetables through the vegetable image discrimination model, and then send the corresponding control signal to the sensor data analysis module.

[0059] It should be noted that the calculation model for vegetable image discrimination is specifically expressed as:

[0060]

[0061] Among them, P(l|I) represents the judgment result that vegetable image I belongs to vegetable category l, l represents the vegetable category of vegetable image I, I represents the image data preprocessed by the vegetable image acquisition module, S(l) represents the judgment function of vegetable category l, L represents the total number of all vegetable categories, l′ represents all possible vegetable categories except vegetable image I, and S(l′) represents the judgment function of vegetable category l′.

[0062] Furthermore, the judgment function of vegetable category l is specifically expressed as:

[0063] S(l)=W×v+b,

[0064] Among them, W represents the weight matrix, v represents the flattened eigenvector, and b represents the braided vector.

[0065] Further, the eigenvalues ​​contained in the flattened eigenvector include the feature mappings of the convolution layer function 0(x, y) and the pooling layer P(x, y). Specifically, in this embodiment, it should be noted that the calculation formula of the convolution layer function is specifically expressed as:

[0066]

[0067] Among them, K(i, j) represents the weight of the convolution kernel, I(x+ik / 2, y+jk / 2) represents the pixel value corresponding to the convolution kernel in the image, and (x, y) represents the position of the pixel being processed; further, the calculation formula of the pooling layer is specifically expressed as:

[0068] P(x,y)=max(O(x+i,y+j)),

[0069] Among them, (x, y) represents the position of the pixel being processed.

[0070] In this embodiment, the vegetable image discrimination module extracts image features through convolution and pooling layers, and then makes a final judgment through a fully connected layer classification composed of weights W and bias b. The discrimination of vegetable image I belonging to vegetable category l is achieved by maximizing the discrimination result P(l|I) of the correct category while minimizing the discrimination results of other categories. For each input image I, a vegetable category l with the highest probability is output as the classification result.

[0071] In this embodiment, the vegetable category judgment module sends an A signal to use spray cleaning if the vegetable category is type A; sends a B signal to use immersion cleaning if the vegetable category is type B; sends a C signal to use steam cleaning if the vegetable category is type C; sends a D signal to use bubble cleaning if the vegetable category is type D; it should be noted that type A represents vegetables with rough or easily damaged surfaces; it should be noted that type B represents harder root vegetables; it should be noted that type C represents vegetables that require gentle disinfection or softening of the skin; it should be noted that type D represents vegetables that require gentle removal of surface dirt while avoiding mechanical damage.

[0072] In this embodiment, the vegetable category judgment module uses a vegetable image discrimination model to accurately identify the category of vegetables to be cleaned, thereby determining the most appropriate cleaning method, ensuring that each vegetable can receive the cleaning treatment that best suits its characteristics, greatly improving the cleaning efficiency and the cleaning quality of the vegetables; based on the vegetable discrimination results, the vegetable category judgment module will send four different control signals to the automatic control unit to start the corresponding cleaning method, effectively improving the cleaning quality, while reducing resource consumption, and achieving a perfect combination of intelligence and environmental protection.

[0073] The sensor data acquisition module is used to obtain relevant information about the environment in which the vegetables to be washed are located and energy consumption information of the washing machine through sensors, form a cleaning information set of the vegetables to be washed and a cleaning machine energy consumption information set, and transmit them to the sensor data analysis module.

[0074] It should be noted that the set of cleaning information of the vegetables to be cleaned is denoted as {H, ph, T}, where H represents the humidity of the cleaning area, ph represents the pH value of the water quality parameter, and T represents the temperature of the cleaning water; further, the set of energy consumption information of the cleaning machine is denoted as {E P(l|I) , P P(l|I) , C P(l|I)} , where E represents the power consumption value under the cleaning mode determined according to the vegetable image recognition result P(l|I), P represents the flushing pressure value under the cleaning mode determined according to the vegetable image recognition result P(l|I), and C represents the amount of water used to clean unit weight of vegetables under the cleaning mode determined according to the vegetable image recognition result P(l|I).

[0075] In this embodiment, the power consumption value during the washing process includes the current consumed per unit mass of vegetables washed and the voltage consumed per unit mass of vegetables washed.

[0076] The sensor data analysis module is used to analyze the cleaning information set of the vegetables to be cleaned and the energy consumption information set of the cleaning machine transmitted by the sensor data acquisition module, and combine the vegetable category judgment module to judge the type of vegetables to be cleaned, obtain the automatic adjustment value of the cleaning agent and the energy consumption value of the cleaning machine, and transmit them to the collaborative analysis module.

[0077] Specifically, it should be noted that the cleaning sensor data analysis module includes an automatic control unit, an energy consumption analysis unit and a recipe database.

[0078] The automatic control unit is used to analyze the data transmitted by the sensor in the sensor data acquisition module and the signal transmitted by the vegetable category judgment module, and adjust the amount of cleaning agent added through the automatic adjustment model.

[0079] It should be noted that the calculation model of the automatic adjustment value of the cleaning agent is specifically expressed as:

[0080]

[0081] Among them, L represents the automatic adjustment value of the cleaning agent, and N represents the total number of times the cleaning is completed. represents the optimal concentration for the i-th cleaning calculated by the automatic adjustment unit, It is represented as the optimal concentration for the i-th cleaning in the formula database.

[0082] Furthermore, the calculation formula of the optimal concentration of the i-th cleaning method calculated by the automatic adjustment unit is specifically expressed as:

[0083] C opt =α1×σ(α2×σ(α1×[H, pH, T, P(l|I)]+b1)+b2)+b3,

[0084] Among them, α1, α2, and α3 represent the preset weights respectively, σ(X) represents the activation function of the automatic adjustment model, [H, ph, T, P(l|I)] represents the input vector of the automatic adjustment model, H represents the humidity of the cleaning area, ph represents the pH value of the water quality parameter, T represents the temperature of the cleaning water, and P(l|I) represents the vegetable image discrimination result.

[0085] Furthermore, the calculation formula of the activation function is expressed as:

[0086]

[0087] Among them, X only represents the input value of the function;

[0088] Furthermore, the quantization function value of the input vector is expressed as:

[0089] [H, pH, T, P(l|I)]=log(H)+e pH +sin(T)+P 3 (l|I),

[0090] Among them, H represents the humidity of the cleaning area, ph represents the pH value of the water quality parameter, T represents the temperature of the cleaning water, and P(l|I) represents the vegetable image discrimination result.

[0091] In this embodiment, once the automatic control unit predicts the optimal concentration, it will adjust the amount of detergent added accordingly to ensure the cleaning effect while avoiding excessive use of chemicals; accurate detergent concentration can effectively remove pollutants on the surface of vegetables while avoiding risks to food safety due to excessive use of chemicals; reasonable use of detergents helps reduce emissions of harmful substances and meets environmental protection requirements; it performs self-optimization through real-time data and feedback, continuously improves its prediction accuracy over time, adjusts the amount of detergent added to improve cleaning efficiency, and reduces chemical waste and lowers operating costs.

[0092] The energy consumption analysis unit is used to analyze the energy consumption information set of the cleaning machine transmitted by the sensor data acquisition module, calculate the energy consumption of the cleaning machine, and transmit it to the collaborative analysis module.

[0093] It should be noted that the calculation model of the energy consumption of the cleaning machine is specifically expressed as

[0094]

[0095] Where γ represents the energy consumption of the washing machine under the washing mode determined according to the vegetable image discrimination result P(l|I), k1 represents the efficiency factor of converting water consumption into energy, k2 represents the efficiency factor of converting pressure into energy, E P(l|I) Expressed as the power consumption value in P(l|I) mode, C P(l|I)It is expressed as the water consumption per unit weight of vegetables washed in the P(l|I) mode, P P(l|I) It is expressed as the flushing pressure value under the P(l|I) mode, k3 is expressed as the efficiency factor of converting time into energy, and t is expressed as the cleaning time.

[0096] In this embodiment, the energy consumption analysis unit can capture the interaction effects between electricity consumption, water usage and flushing pressure by introducing cross terms, and can more realistically reflect the energy consumption change law in the actual cleaning process, thereby improving the predictive ability and applicability of the model. It can accurately reflect the diminishing marginal benefits of the increase in electricity consumption and water usage when the flushing pressure exceeds a certain threshold, which helps to optimize the flushing pressure setting, avoid unnecessary energy waste, and improve cleaning efficiency; through the impact of efficiency attenuation on energy consumption, it helps equipment maintenance planning and rational allocation of resources, to ensure the economy and reliability of long-term operation; through refined energy consumption analysis, it can provide a scientific basis for the operation of the cleaning machine, and can effectively guide the optimization of cleaning parameters, thereby achieving the goal of energy conservation and emission reduction.

[0097] The recipe database is used to store the ideal cleaning parameters for various vegetables, including cleaning methods, optimal concentration of cleaning agents, etc.

[0098] It should be noted that the formula database is based on a large amount of sample data to ensure that each vegetable receives the cleaning treatment that best suits its characteristics; when the vegetable category judgment module identifies the type of vegetable, the automatic control unit queries the formula database and retrieves the cleaning formula that matches the vegetable type; the actual optimal concentration data is used to train the automatic adjustment model to help the model learn the optimal amount of cleaning agent for different vegetable types; by comparing the model prediction and the actual optimal concentration, the weights are continuously optimized to improve the accuracy of the prediction; the formula database has an update mechanism that can be expanded and adjusted with the emergence of new vegetable varieties or the advancement of cleaning technology; by precisely controlling the use of cleaning agents, the formula database indirectly promotes the effective use of resources and cost control, reduces unnecessary chemical consumption, and avoids food safety risks.

[0099] The collaborative analysis module is used to analyze the data information transmitted by the sensor data analysis module, build a collaborative analysis function model, and evaluate the cleaning effect of the vegetable washing machine.

[0100] It should be noted that the collaborative analysis function model is specifically expressed as:

[0101]

[0102] Among them, CAFV represents the collaborative analysis function value, L represents the automatic adjustment value of the cleaning agent, K represents the influencing factor of data collection, M represents the total number of cleaning methods, γ j It is expressed as the energy consumption of the cleaning machine under the j-th cleaning mode, It is expressed as the energy consumption of the cleaning machine under the jth cleaning mode under ideal conditions.

[0103] In this embodiment, CAFV is used to evaluate the comprehensive index of the operation control of the intelligent vegetable washing machine, which integrates the energy consumption deviation, cleaning efficiency and possible normalization factors. The smaller the calculated value, the smaller the deviation between the actual energy consumption and the expected energy consumption, and the better the efficiency and control effect of the cleaning process.

[0104] Furthermore, the energy consumption of the cleaning machine under ideal conditions in the jth cleaning mode is calculated based on the average of historical data, and the collaborative analysis function model It is expressed as the error between the automatic adjustment of the cleaning agent and the expected value. It is expressed as the difference between the energy consumption of the cleaning machine and the expected value.

[0105] In this embodiment, the collaborative analysis module can provide a comprehensive evaluation of the cleaning effect by comprehensively analyzing multi-source data, can provide refined guidance for the operation and maintenance of the vegetable washing machine, improve cleaning efficiency and resource utilization, ensure fine adjustment of cleaning parameters, avoid excessive consumption of resources, and also ensure the cleaning quality of vegetables; by revealing the mechanism of action of factors affecting data collection, the unit can promote the understanding and optimization of the cleaning process, and can promote the innovation and development of cleaning technology; by continuously monitoring and evaluating the cleaning effect, it can achieve dynamic optimization of the cleaning process, can effectively prevent and solve cleaning quality problems, and improve customer satisfaction.

[0106] The user feedback module is used to obtain the terminal user's evaluation of the cleaning effect, determine the deviation of the cleaning effect using the collaborative analysis function value transmitted by the collaborative analysis module, and provide timely feedback on abnormal cleaning effects.

[0107] It should be noted that the user feedback module obtains direct evaluations from users under different vegetable types and different cleaning modes. When the cleaning effect is abnormal, that is, it does not meet the user's expectations, the user feedback module triggers an alarm and analyzes possible reasons to further adjust the cleaning parameters; what needs to be specifically noted in the present embodiment is that the reasons for the abnormal cleaning effect include improper setting of cleaning parameters, hardware failure, and the need to replace consumables; what needs to be specifically noted in the present embodiment is that the cleaning parameters that need to be adjusted when the cleaning effect is abnormal include water pressure, detergent concentration, cleaning time and temperature.

[0108] In this embodiment, the user feedback module improves the cleaning effect and customer satisfaction by adjusting and optimizing the cleaning parameters, ensuring that the intelligent vegetable cleaning machine can continuously adapt to the needs of different vegetable types and cleaning modes, and achieve an efficient, energy-saving and user-friendly cleaning process.

[0109] Further, the steps for obtaining the terminal user's evaluation of the cleaning effect, determining the deviation of the cleaning effect using the collaborative analysis function value transmitted by the collaborative analysis module, and providing feedback on the abnormal cleaning effect in a timely manner include:

[0110] Pre-set user evaluation results, and set the user evaluation results as exceeding cleaning expectations, meeting cleaning expectations, and failing to meet cleaning expectations;

[0111] When the evaluation of the cleaning effect obtained by the terminal user is that it exceeds the cleaning expectation or does not meet the cleaning expectation, the actual cleaning information set and the actual cleaning operation parameters of the vegetables that have completed the cleaning operation are counted;

[0112] Based on the actual cleaning information set and the actual cleaning operation parameters, the vegetable category judgment module and the sensor data analysis module are modified.

[0113] In the technical scheme, there is further provided a step for obtaining the evaluation of the cleaning effect by the terminal user, determining the deviation of the cleaning effect by using the collaborative analysis function value transmitted by the collaborative analysis module, and timely providing feedback on the abnormal cleaning effect. After the cleaning is completed, the display unit can display options for the user to input the evaluation of the cleaning effect by the terminal user. The specific options may include exceeding the cleaning expectation, meeting the cleaning expectation, and not meeting the cleaning expectation. When the option used for input is in line with the cleaning expectation, the result of the cleaning judged by the user is the same as the result of the cleaning judged by the operation control system of the intelligent vegetable washing machine based on the Internet of Things. When the option input by the user is exceeding the cleaning expectation or not meeting the cleaning expectation, it can be explained that there is a difference between the result of the cleaning judged by the user and the structure of the cleaning judged by the operation control system of the intelligent vegetable washing machine based on the Internet of Things. In this case, the cleaning process of the vegetable can be called, that is, the actual cleaning information set and actual cleaning operation parameters of the vegetables of the cleaning operation are obtained, and then the vegetable category judgment module and the sensor data analysis module are corrected based on these parameters, so that the vegetable category judgment module and the sensor data analysis module can be continuously optimized, and the application of the operation control system of the intelligent vegetable washing machine based on the Internet of Things can be made more accurate.

[0114] As attached Figure 3 The operation control method of an intelligent vegetable washing machine based on the Internet of Things shown includes the following steps:

[0115] S1. Collecting vegetable images: Capturing images of the vegetable washing area through a high-definition camera, pre-processing the collected images, converting the images from analog signals into digital signals and transmitting them to the vegetable category judgment module;

[0116] S2, discriminating the vegetable category: receiving the image data of the vegetables to be cleaned in the vegetable image collection, discriminating the category of the vegetables through the vegetable image discrimination model, and sending the corresponding control signal to the data analysis;

[0117] S3, collecting sensor data: obtaining relevant information of the environment of the vegetables to be washed and energy consumption information of the washing machine through sensors, forming a set of washing information of the vegetables to be washed and a set of energy consumption information of the washing machine, and transmitting them to data analysis;

[0118] S4, analyzing sensor data: analyzing the cleaning information set of the vegetables to be cleaned and the energy consumption information set of the cleaning machine transmitted by the data acquisition, combining the vegetable identification with the type identification of the vegetables to be cleaned, obtaining the automatic adjustment value of the cleaning agent and the energy consumption value of the cleaning machine, and transmitting them to the collaborative analysis;

[0119] S5. Analyze the synergistic effect: Analyze the data information transmitted by the data analysis, build a synergistic analysis function model, and evaluate the cleaning effect of the vegetable washing machine;

[0120] S6. Obtain user feedback: Obtain the terminal user's evaluation of the cleaning effect, use the collaborative analysis function value transmitted by the collaborative analysis to determine the deviation of the cleaning effect, and provide feedback on abnormal cleaning effects in a timely manner.

[0121] Secondly: In the drawings of the embodiments disclosed in the present invention, only the structures related to the embodiments disclosed in the present invention are involved, and other structures can refer to the general design. In the absence of conflict, the same embodiment and different embodiments of the present invention can be combined with each other;

[0122] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. An intelligent vegetable washing machine operation control system based on the Internet of Things, characterized in that: include: Vegetable image acquisition module: used to capture images of the vegetable washing area through a high-definition camera, pre-process the acquired images, convert the images from analog signals into digital signals and transmit them to the vegetable category judgment module; Vegetable category judgment module: used to receive the image data of the vegetables to be cleaned in the vegetable image acquisition module, identify the category of the vegetables through the vegetable image discrimination model, and send the corresponding control signal to the sensor data analysis module; Sensor data acquisition module: used to obtain relevant information of the environment in which the vegetables to be washed are located and energy consumption information of the washing machine through sensors, form a set of washing information of the vegetables to be washed and a set of energy consumption information of the washing machine, and transmit them to the sensor data analysis module; Sensor data analysis module: used to analyze the cleaning information set of the vegetables to be cleaned and the energy consumption information set of the cleaning machine transmitted by the sensor data acquisition module, and combine the type of the vegetables to be cleaned determined by the vegetable category determination module to obtain the automatic adjustment value of the cleaning agent and the energy consumption value of the cleaning machine, and transmit them to the collaborative analysis module; including an automatic control unit, an energy consumption analysis unit, and a recipe database; Collaborative analysis module: used to analyze the data information transmitted by the sensor data analysis module, build a collaborative analysis function model, and evaluate the cleaning effect of the vegetable washing machine; User feedback module: used to obtain the terminal user's evaluation of the cleaning effect, determine the deviation of the cleaning effect using the collaborative analysis function value transmitted by the collaborative analysis module, and provide timely feedback on abnormal cleaning effects.

2. According to claim 1, an intelligent vegetable washing machine operation control system based on the Internet of Things is characterized by: The preprocessing steps of the vegetable image acquisition module include: A1. Remove noise through filters and adjust brightness and contrast by adjusting pixel values ​​to improve image quality; A2. Through computer vision technology, the characteristics of vegetables are extracted from the image, and the analog signal of the image is converted into a digital signal. The digital signal of the image is represented by the grayscale value of the pixel located in the x-th column and the grayscale value of the pixel in the y-th row in the image I, denoted as I(x, y), where x represents the width of the image, that is, the number of pixels in the horizontal direction of the image, and y represents the length of the image, that is, the number of pixels in the vertical direction of the image.

3. According to the Internet of Things-based intelligent vegetable washing machine operation control system of claim 1, it is characterized by: The calculation model for judging the vegetable category is specifically expressed as follows: Among them, P(l|I) represents the judgment result that vegetable image I belongs to vegetable category l, l represents the vegetable category of vegetable image I, I represents the image data preprocessed by the vegetable image acquisition module, S(l) represents the judgment function of vegetable category l, L represents the total number of all vegetable categories, l′ represents all possible vegetable categories except vegetable image I, and S(l′) represents the judgment function of vegetable category l′.

4. According to claim 1, the operation control system of an intelligent vegetable washing machine based on the Internet of Things is characterized by: The vegetable category judgment module sends an A signal and uses spray cleaning if the vegetable category is type A; sends a B signal and uses immersion cleaning if the vegetable category is type B; sends a C signal and uses steam cleaning if the vegetable category is type C; sends a D signal and uses bubble cleaning if the vegetable category is type D; Type A represents vegetables with rough or easily damaged surfaces; Type B represents harder root vegetables; Type C represents vegetables that require gentle disinfection or softening of the skin; Type D represents vegetables that require gentle removal of surface dirt while avoiding mechanical damage.

5. According to the Internet of Things-based intelligent vegetable washing machine operation control system of claim 1, it is characterized by: The cleaning information set of the vegetables to be cleaned is denoted as {H, ph, T}, where H represents the humidity of the cleaning area, ph represents the pH value of the water quality parameter, and T represents the temperature of the cleaning water; the energy consumption information set of the cleaning machine is denoted as {E P(l|I) , P P(l|I) , C P(l|I) }, wherein E represents the power consumption value in the cleaning mode determined according to the vegetable image recognition result P(l|I), P represents the flushing pressure value in the cleaning mode determined according to the vegetable image recognition result P(l|I), and C represents the amount of water used to clean unit weight of vegetables in the cleaning mode determined according to the vegetable image recognition result P(l|I).

6. According to the Internet of Things-based intelligent vegetable washing machine operation control system of claim 1, it is characterized by: The calculation model of the automatic adjustment value of the cleaning agent is specifically expressed as follows: Where L represents the automatic adjustment value of the cleaning agent, and N represents the total number of times the cleaning is completed. represents the optimal concentration for the i-th wash calculated by the automatic adjustment unit, It is represented as the optimal concentration for the i-th cleaning in the formula database; Furthermore, the calculation formula of the optimal concentration of the i-th cleaning method calculated by the automatic adjustment unit is specifically expressed as: C opt =α1×σ(α2×σ(α1×[H,pH,T,P(l|I)]+b1)+b2)+b3, Among them, α1, α2, α3 represent the preset weights respectively, b1, b2, b3 represent the preset coefficients respectively, σ(x) represents the activation function of the automatic adjustment model, [H, ph, T, P(l|I)] represents the input vector of the automatic adjustment model, H represents the humidity of the cleaning area, ph represents the pH value of the water quality parameter, T represents the temperature of the cleaning water, and P(l|I) represents the vegetable image discrimination result.

7. According to the Internet of Things-based intelligent vegetable washing machine operation control system of claim 1, it is characterized by: The calculation model of the energy consumption of the cleaning machine is specifically expressed as follows: Where γ represents the energy consumption of the washing machine under the washing mode determined according to the vegetable image discrimination result P(l|I), k1 represents the efficiency factor of converting water consumption into energy, k2 represents the efficiency factor of converting pressure into energy, E e P(l|I) Expressed as the power consumption value in P(l|I) mode, C e P(l|I) It is expressed as the water consumption per unit weight of vegetables washed in the P(l|I) mode, P e P(l|I) It is expressed as the flushing pressure value under the P(l|I) mode, k3 is expressed as the efficiency factor of converting time into energy, and t is expressed as the cleaning time.

8. The operation control system of an intelligent vegetable washing machine based on the Internet of Things according to claim 1 is characterized in that: The collaborative analysis function model is specifically expressed as follows: Among them, CAFV represents the collaborative analysis function value, L represents the automatic adjustment value of the cleaning agent, κ represents the influencing factor of data collection, M represents the total number of cleaning methods, γ j It is expressed as the energy consumption of the cleaning machine under the j-th cleaning mode, It is expressed as the energy consumption of the cleaning machine under the jth cleaning mode under ideal conditions.

9. An operation control system for an intelligent vegetable washing machine based on the Internet of Things according to any one of claims 1 to 8, characterized in that: The steps for obtaining the evaluation of the cleaning effect by the terminal user, determining the deviation of the cleaning effect by using the collaborative analysis function value transmitted by the collaborative analysis module, and providing feedback on the abnormal cleaning effect in a timely manner include: Pre-set user evaluation results, and set the user evaluation results as exceeding cleaning expectations, meeting cleaning expectations, and failing to meet cleaning expectations; When the evaluation of the cleaning effect obtained by the terminal user is that it exceeds the cleaning expectation or does not meet the cleaning expectation, the actual cleaning information set and the actual cleaning operation parameters of the vegetables that have completed the cleaning operation are counted; Based on the actual cleaning information set and the actual cleaning operation parameters, the vegetable category judgment module and the sensor data analysis module are modified.

10. An operation control method of an intelligent vegetable washing machine based on the Internet of Things, according to the operation control system of an intelligent vegetable washing machine based on the Internet of Things described in any one of claims 1 to 9, characterized in that: The following steps are involved: S1. Collecting vegetable images: Capturing images of the vegetable washing area through a high-definition camera, pre-processing the collected images, converting the images from analog signals into digital signals and transmitting them to the vegetable category judgment module; S2, discriminating the vegetable category: receiving the image data of the vegetables to be cleaned in the vegetable image collection, discriminating the category of the vegetables through the vegetable image discrimination model, and sending the corresponding control signal to the data analysis; S3, collecting sensor data: obtaining relevant information of the environment of the vegetables to be washed and energy consumption information of the washing machine through sensors, forming a set of washing information of the vegetables to be washed and a set of energy consumption information of the washing machine, and transmitting them to data analysis; S4, analyzing sensor data: analyzing the cleaning information set of the vegetables to be cleaned and the energy consumption information set of the cleaning machine transmitted by the data acquisition, combining the vegetable identification with the type identification of the vegetables to be cleaned, obtaining the automatic adjustment value of the cleaning agent and the energy consumption value of the cleaning machine, and transmitting them to the collaborative analysis; S5. Analyze the synergistic effect: Analyze the data information transmitted by the data analysis, build a synergistic analysis function model, and evaluate the cleaning effect of the vegetable washing machine; S6. Obtain user feedback: Obtain the terminal user's evaluation of the cleaning effect, use the collaborative analysis function value transmitted by the collaborative analysis to determine the deviation of the cleaning effect, and provide feedback on abnormal cleaning effects in a timely manner.

Images