A local incremental iterative dishwasher control method and system

Abstract

This invention discloses a local incremental iterative dishwasher control method and system. The method includes: detecting the load status; setting current washing parameters, including water temperature, water pressure, set washing time, and detergent dosage; starting washing based on the current washing parameters; measuring cleanliness data, including final turbidity value, washing time, and operating energy consumption; and adaptively adjusting the current washing parameters based on the cleanliness data. Thus, turbidity, energy consumption, and other parameters are measured in real time during the washing process, and the local AI model adaptively adjusts the washing parameters accordingly, significantly reducing water and detergent consumption and lowering overall energy consumption while ensuring thorough cleaning. Furthermore, the local AI model does not communicate with external systems, performing incremental iterations only locally, and its operation is unaffected by network conditions, thus preventing the leakage of user data.

Description

Technical Field

[0001] This invention relates to the field of intelligent control technology, and in particular to a local incremental iterative dishwasher control method and system. Background Technology

[0002] When using a dishwasher, the washing settings need to be adjusted according to the quantity and grease level of the dishes. This includes adjusting the water temperature, water pressure, washing time, and detergent dosage. Traditional dishwashers typically have several preset settings, and their cleaning strategy is to exceed the recommended level by using longer washing times, more detergent, and higher flow rates and water pressure to ensure thorough cleaning. This inevitably leads to water and energy waste, and if the user sets the settings incorrectly, the dishes may not even get clean.

[0003] To address this, existing AI solutions developed for dishwashers can autonomously detect washing conditions and adaptively adjust washing parameters without requiring manual user intervention. However, current local AI solutions only support inference using fixed pre-trained models. The model weights are fixed after the device leaves the factory, making it impossible to iteratively optimize based on user habits. They can only adjust washing parameters based on preset rules, failing to adapt to variations in household grease levels, washing habits, and water quality, resulting in significant water and energy waste. Cloud-based AI solutions, relying on continuously updated large models for accurate detection and flexible control, require a stable internet connection for the dishwasher. In poor network conditions, they can only operate based on a fixed local program, and the process requires uploading user data, posing a privacy risk. Summary of the Invention

[0004] Embodiment 1 of the present invention discloses a local incremental iterative dishwasher control method, specifically including: Detect the load status and set the current washing parameters, including water temperature, water pressure, washing set duration and detergent dosage; The washing process is started based on the current washing parameters, and the cleanliness data is measured. The cleanliness data includes the final turbidity value, washing time, and operating energy consumption. The current washing parameters are adaptively adjusted based on the cleanliness data.

[0005] As an optional implementation, the method further includes: When the cleanliness data indicates that washing is complete, collect the final washing parameters; Local incremental iteration is performed based on the final washing parameters.

[0006] As an optional implementation, the local incremental iteration based on the final washing parameters includes: Calculate the gain and error of the final washing parameters, and generate a loss function; The neural network weights are updated based on the convergence value of the loss function.

[0007] As an optional implementation, the final turbidity value is measured by an optical turbidity sensor for the washing circulating water to characterize the residual oil and residue on the surface of the tableware. The operating energy consumption is measured by a Hall current sensor for the power supply circuit of the spray pump and the main control circuit board, and is used to characterize the overall energy consumption data of the machine during the washing cycle.

[0008] As an optional implementation, the method further includes: Based on the measured operating energy consumption of the power supply circuit of the spray pump, the current fluctuation characteristics are analyzed. The load condition is obtained by analyzing the current fluctuation characteristics. The load conditions include the number of tableware and the stacking status of the tableware.

[0009] As an optional implementation, the method further includes: The water level inside the washing chamber is measured using a water level sensor; Based on the load and the internal water level, the current washing parameters are set.

[0010] As an optional implementation, the method further includes: The damage data, the corresponding damage value, and the visualization report are input into the quantification model.

[0011] Embodiment 2 of the present invention discloses a local incremental iterative dishwasher control system, characterized in that it includes: The detection module is used to detect the load condition and set the current washing parameters based on the load condition. The washing parameters include water temperature, water pressure, washing set time and detergent dosage. The washing module starts the washing process based on the current washing parameters; The detection module is also used to measure cleanliness data during the washing process, including final turbidity value, washing time and operating energy consumption. An adaptive module is used to adaptively adjust the current washing parameters based on the cleanliness data.

[0012] As an optional implementation, the adaptive module is also used to collect final washing parameters when the cleanliness data indicates that washing is complete, and to perform local incremental iteration based on the final washing parameters.

[0013] As an optional implementation, the adaptive module employs a fixed lightweight CNN model or a shallow Transformer neural network model and is not connected to or transmit data to external execution data.

[0014] Compared with the prior art, this embodiment has the following beneficial effects: In this embodiment, parameters such as turbidity and energy consumption are measured in real time during the washing process. The local AI model adaptively adjusts the washing parameters accordingly, significantly reducing water and detergent consumption while ensuring thorough cleaning and lowering overall energy consumption. Furthermore, the local AI model does not communicate with external systems, performing incremental iterations only locally. Its operation is unaffected by network conditions and does not leak user data. Attached Figure Description

[0015] To more clearly illustrate the technical solutions in this embodiment, the accompanying drawings used in the embodiment will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0016] Figure 1 This is a schematic diagram of the workflow of a local incremental iterative dishwasher control method disclosed in Embodiment 1; Figure 2 This is a schematic diagram of the system structure of a dishwasher control system with local incremental iteration disclosed in Embodiment 2. Detailed Implementation

[0017] The technical solutions in this embodiment will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0018] Example 1 Please see Figure 1 This embodiment discloses a local incremental iterative dishwasher control method, including: S1. Detect the load and set the current washing parameters.

[0019] In this embodiment, the washing parameters include water temperature, water pressure, washing time setting, and detergent dosage.

[0020] As an optional implementation method, the current fluctuation characteristics are analyzed based on the operating energy consumption measured for the power supply circuit of the spray pump. Based on the characteristics of current fluctuations, the load conditions are analyzed; The load information includes the number of tableware items and their stacking status.

[0021] Specifically, the driving load of the spray pump differs when it is pressurizing and spraying the tableware in an empty area. By analyzing the current fluctuation characteristics, the load of the tableware in the washing chamber can be determined.

[0022] Taking the initial spraying stage as an example, by collecting the current fluctuation characteristics of the power supply circuit of the spray water pump during the single complete spraying of the entire washing chamber by the nozzle, the stacking status of tableware in each area of ​​the washing chamber can be known.

[0023] For example, when the nozzle passes through an area with multiple densely stacked discs, the current fluctuation characteristics will show a peak with increased load, while when passing through an empty area, the current fluctuation characteristics will show a trough with decreased load.

[0024] Furthermore, in the washing chamber, the plate is higher than the bowl and closer to the nozzle, so the peak corresponding to the plate in the current fluctuation characteristics will be higher than the peak corresponding to the bowl. This transformation analysis can be used to obtain the tableware stacking state.

[0025] Furthermore, the tableware is placed based on the limited space of the dish rack, with sufficient gaps between adjacent tableware to achieve spraying and washing without dead angles. Therefore, in the current fluctuation characteristics, there will be troughs corresponding to the gaps between the peaks of the tableware, which can be used to roughly estimate the number of tableware.

[0026] As an optional implementation, a water level sensor is used to measure the internal water level of the washing chamber; Set the current washing parameters based on the load and internal water level.

[0027] Specifically, the water level can be monitored and controlled to ensure that the amount of circulating water in the washing chamber is at a reasonable level, and the concentration of detergent in the washing water can be ensured in conjunction with the amount of detergent added, so as to obtain a good washing effect.

[0028] In summary, based on the measured number of tableware, the stacking status of the tableware, the internal water level, and other detailed information, washing parameters can be initially set. For example, when there are a large number of tableware and they are stacked densely, the spray water temperature and water pressure can be appropriately increased, the washing time can be extended, and the amount of detergent added can be increased.

[0029] S2. Start washing based on current washing parameters and measure cleanliness data.

[0030] In this embodiment, the current washing parameters set in step S1 are values ​​set after evaluation, and therefore are likely to be inaccurate. If washing is performed based on the current washing parameters, it is very likely that the washing will not be clean or the washing will continue even after the washing is clean. Therefore, it is necessary to measure the cleanliness data in real time during the washing process and analyze whether there is a deviation between the actual situation and the set current washing parameters.

[0031] In this embodiment, the cleanliness data includes the final turbidity value, washing time, and operating energy consumption; Specifically, the final turbidity value is measured by an optical turbidity sensor for the washing circulating water, and is used to characterize the residual oil and residue on the surface of the tableware. The operating energy consumption is measured by Hall current sensors for the power supply circuit of the spray pump and the main control circuit board, which is used to characterize the overall energy consumption data of the machine during the washing cycle.

[0032] Understandably, the final turbidity value can directly reflect the turbidity of the recycled water. When there is a lot of oil and residue on the tableware, the same volume of recycled water will be more turbid.

[0033] Therefore, the accuracy of the degree of dirt corresponding to the current washing parameters can be determined based on the final value of the turbidity of the circulating water.

[0034] Furthermore, the washing time also affects the degree of cleaning. If the degree of dirt on the tableware deviates from expectations, the washing time will be adjusted accordingly based on the washing time.

[0035] Furthermore, the operating energy consumption can be statistically analyzed over a long period of time, and performance optimization and adjustment can be achieved accordingly.

[0036] S3. Adaptively adjust the current washing parameters based on cleanliness data.

[0037] In this embodiment, based on the cleanliness data measured during the washing process, the current washing parameters will be adjusted adaptively in real time, rather than waiting for the current washing process to end before making adjustments.

[0038] As an optional implementation, when the cleanliness data indicates that washing is complete, the final washing parameters are collected; Local incremental iteration is performed based on the final washing parameters.

[0039] This includes local incremental iteration based on the final washing parameters, including: Calculate the final washing parameters' gains and errors, and generate a loss function; The neural network weights are updated based on the convergence value of the loss function.

[0040] Here, the cleanliness data generated during the washing process will be continuously used for local incremental iteration, achieving the effect of "washing and adjusting at the same time". Users do not need to manually set specific washing levels or pay attention to the washing effect during the washing process, which can ensure that the final washing is clean and without wasting washing water and detergent.

[0041] In addition, based on local incremental iteration, the operation and maintenance will obtain a washing database corresponding to the current user. Thus, in the long-term use, the neural network weights will be fitted and adjusted according to the user's cooking habits, diet, cleaning level, etc., and the current washing parameters will be more accurate, significantly improving the user experience.

[0042] Here, based on the same load conditions and the same current washing parameters, the following situations may occur when facing different users: A. For heavily soiled dishes, the tableware has a lot of solidified grease, protein and other substances adhering to it. At this time, the current washing parameters are not enough to clean it. The cleaning data will show that the final turbidity value is higher and the operating energy consumption is higher under the same washing time. Therefore, the water temperature, water pressure, washing time setting and detergent dosage are adaptively adjusted to ensure the cleaning effect.

[0043] For lightly oily surfaces, where only a small amount of water stains and rice residue may remain on the tableware, continuing to wash based on the current washing parameters would waste recycled water and detergent. Cleanliness data will show that the final turbidity value is significantly reduced under the same washing time. Therefore, the water temperature, water pressure, washing time setting, and detergent dosage are adaptively adjusted. When the final turbidity value indicates that the tableware is clean, the washing will stop, effectively saving water and detergent.

[0044] Understandably, in addition to adaptive adjustment based on turbidity, other parameters can be introduced for comprehensive evaluation.

[0045] For example, the quality of tap water varies from place to place, and some households have pre-filters installed. The ion concentration in the recycled water will affect the foam generation during the washing process, thus affecting the washing effect. Therefore, TDS and other values ​​of the recycled water can be measured to adjust the amount of water and detergent accordingly.

[0046] In this embodiment, parameters such as turbidity and energy consumption are measured in real time during the washing process. The local AI model adaptively adjusts the washing parameters accordingly, significantly reducing water and detergent consumption while ensuring thorough cleaning and lowering overall energy consumption. Furthermore, the local AI model does not communicate with external systems, performing incremental iterations only locally. Its operation is unaffected by network conditions and does not leak user data.

[0047] Example 2 Please see Figure 2 The system disclosed in this embodiment includes: The detection module is used to detect the load condition and set the current washing parameters based on the load condition. The washing parameters include water temperature, water pressure, washing set time and detergent dosage. The washing module starts the washing process based on the current washing parameters; The detection module is also used to measure cleanliness data during the washing process, including final turbidity value, washing time and operating energy consumption. The adaptive module is used to adaptively adjust the current washing parameters based on cleanliness data.

[0048] In this embodiment, the adaptive module is also used to collect the final washing parameters when the cleanliness data indicates that washing is complete, and to perform local incremental iteration based on the final washing parameters.

[0049] In this embodiment, the adaptive module uses a fixed lightweight CNN model or a shallow Transformer neural network model, and does not connect to or transmit data with external execution data.

[0050] Accordingly, the adaptive module maintains a local incremental iterative AI model, which dynamically adjusts the current washing parameters during the washing process and updates them based on historical washing data, so that the current washing parameters set for each wash are more in line with the user's cooking and eating habits.

[0051] Furthermore, the AI ​​model that performs local incremental iterations does not communicate with the outside world and only performs incremental iterations locally. The operation is not affected by the network environment, and even if the network environment fluctuates, it will not affect the washing process.

[0052] Furthermore, locally deployed adaptive modules do not leak user data, possess reliable security, and can effectively prevent malicious intrusions through network ports.

Claims

1. A local incremental iterative dishwasher control method, characterized in that, include: Detect the load status and set the current washing parameters, including water temperature, water pressure, washing set duration and detergent dosage; The washing process is started based on the current washing parameters, and the cleanliness data is measured. The cleanliness data includes the final turbidity value, washing time, and operating energy consumption. The current washing parameters are adaptively adjusted based on the cleanliness data.

2. The dishwasher control method with local incremental iteration according to claim 1, characterized in that, The method further includes: When the cleanliness data indicates that washing is complete, collect the final washing parameters; Local incremental iteration is performed based on the final washing parameters.

3. The local incremental iterative dishwasher control method according to claim 2, characterized in that, The local incremental iteration based on the final washing parameters includes: Calculate the gain and error of the final washing parameters, and generate a loss function; The neural network weights are updated based on the convergence value of the loss function.

4. The dishwasher control method with local incremental iteration according to claim 1, characterized in that, include: The final turbidity value is measured by an optical turbidity sensor for the washing circulating water, and is used to characterize the residual oil and residue on the surface of the tableware. The operating energy consumption is measured by a Hall current sensor for the power supply circuit of the spray pump and the main control circuit board, and is used to characterize the overall energy consumption data of the machine during the washing cycle.

5. The dishwasher control method with local incremental iteration according to claim 4, characterized in that, The method further includes: Based on the measured operating energy consumption of the power supply circuit of the spray pump, the current fluctuation characteristics are analyzed. The load condition is obtained by analyzing the current fluctuation characteristics. The load conditions include the number of tableware and the stacking status of the tableware.

6. The dishwasher control method with local incremental iteration according to claim 5, characterized in that, The method further includes: The water level inside the washing chamber is measured using a water level sensor; Based on the load and the internal water level, the current washing parameters are set.

7. A local incremental iterative dishwasher control system, characterized in that, include: The detection module is used to detect the load condition and set the current washing parameters based on the load condition. The washing parameters include water temperature, water pressure, washing set time and detergent dosage. The washing module starts the washing process based on the current washing parameters; The detection module is also used to measure cleanliness data during the washing process, including final turbidity value, washing time and operating energy consumption. An adaptive module is used to adaptively adjust the current washing parameters based on the cleanliness data.

8. A local incremental iterative dishwasher control system according to claim 7, characterized in that, include: The adaptive module is also used to collect final washing parameters when the cleanliness data indicates that washing is complete, and to perform local incremental iteration based on the final washing parameters.

9. A local incremental iterative dishwasher control system according to claim 8, characterized in that, include: The adaptive module employs a fixed lightweight CNN model or a shallow Transformer neural network model and does not connect to or transmit data with external execution data.

Images