Kitchen cooking linkage control system

Abstract

The invention provides a kitchen cooking linkage control system. The kitchen cooking linkage control system comprises a data acquisition module, a data classification module, a fault early warning module and a fault output module, the intelligent kitchen equipment linkage control is realized, the causal relationship of the system fault is displayed in a graphical manner through the fault tree early warning model, the logic relationship among various factors in a complex system can be clearly expressed, the fault detection of the range hood is realized, and the fault detection efficiency is improved. According to the kitchen linkage control system, the smoke exhauster and the communication state between the smoke exhauster and the kitchen equipment are detected, whether faults exist or not can be found in time, normal operation of the kitchen linkage control system is guaranteed, the system is analyzed on the whole, and powerful support is provided for optimization and decision making of the system.

Description

Technical Field

[0001] The present invention relates to the field of kitchen appliances, and particularly to a kitchen cooking linkage control system. Background Art

[0002] Since the birth of mankind, diet and its cooking skills have been continuously developed and improved along with human history. People have developed various recipes and corresponding cooking techniques. The types of dishes and kitchen equipment selected for different recipes are different. With the continuous increase of user needs, kitchen equipment has gradually developed towards the direction of intelligence, and the linkage control between different kitchen equipment has been realized, which makes people's cooking become more simple and efficient. While the intelligent kitchen equipment brings great convenience to people's lives, it also brings some problems. Among them, the range hood has a high usage frequency in the kitchen and is also relatively closely linked with other kitchen equipment. If a failure occurs to the range hood during cooking, the fumes in the kitchen cannot be exhausted, thus affecting the cooking environment. The existing intelligent kitchen linkage control system does not have the function of detecting the failure of the range hood and the function of detecting the communication status between the range hood and other kitchen equipment. Therefore, it is necessary to design an intelligent kitchen cooking linkage control system with the function of detecting the failure of the range hood and the function of detecting the communication status between the range hood and other kitchen equipment. Summary of the Invention

[0003] To solve the above problems, the present invention provides a kitchen cooking linkage control system, which can detect the failure of the range hood and can also detect the communication status between the range hood and kitchen equipment, so as to timely discover whether there is a failure and ensure the normal operation of the kitchen linkage control system.

[0004] To achieve the above object, the technical solution adopted by the present invention is:

[0005] A kitchen cooking linkage control system includes a data acquisition module, a data classification module, a fault warning module, and a fault output module;

[0006] The data acquisition module: is used to collect and integrate the data information collected by the sensor network and the data information of communication between devices;

[0007] The data classification module: classifies the data collected by the sensor network based on the fuzzy clustering analysis model and divides it into different groups;

[0008] The fault warning module: respectively performs fault monitoring on different monitoring objects and outputs a warning signal;

[0009] Based on the data of the first group, the threshold judgment algorithm is used to judge whether there is a fault in the motor;

[0010] Based on the second type of group data, perform consistency checks on the sensor data to detect whether the sensor is faulty; based on the third type of group data, use a trend analysis algorithm to analyze the changing trends of the pressure and wind speed data,

[0011] to determine whether the air duct is blocked;

[0012] Based on the fourth type of group data, based on the fault tree warning model, adopt a heartbeat packet mechanism to detect the communication status between devices;

[0013] Fault output module: Alarm for faults according to the warning signal and generate a fault detection report.

[0014] The data acquisition module uses a sensor network to collect data. The sensor network includes a current sensor connected in series in the range hood motor circuit, a voltage sensor connected in parallel in the range hood motor circuit, a rotation speed sensor installed on the motor shaft, a smoke sensor, a pressure sensor and a wind speed sensor installed in the air duct.

[0015] In the data classification module, the data is divided into different groups based on the fuzzy clustering analysis model. The specific steps include:

[0016] Collect the voltage, current, rotation speed, smoke, pressure and wind speed data measured by the sensors to form a data set;

[0017] Perform normalization processing on the data;

[0018] Establish a fuzzy similarity matrix, use the similarity measurement method based on Euclidean distance to process the data samples, obtain the Euclidean distance, convert the distance into a similarity coefficient, obtain the similarity matrix, and judge the similarity degree between different data samples;

[0019] Determine the initial membership matrix of fuzzy clustering, classify the processed data according to the similarity degree, and randomly generate an initial fuzzy membership matrix;

[0020] Iteratively calculate the cluster centers and the membership matrix. According to the current membership matrix, calculate the center of each cluster. According to the new cluster centers, update the membership matrix. Repeat the above two steps until the change in the membership matrix is less than a preset threshold or the maximum number of iterations is reached;

[0021] According to the final membership matrix, determine the cluster membership of each data sample.

[0022] In the fault warning module, the collected current, voltage, and rotational speed signals are subjected to mean filtering, and a threshold judgment algorithm is used to determine whether the motor has a fault. According to the rated parameters and normal operating range of the motor, the thresholds of current, voltage, and rotational speed are set. When the monitored data exceeds the threshold range, it is determined that the motor has a fault.

[0023] In the fault warning module, the classified third - type group data is divided into a training set and a test set;

[0024] The selected moving average method algorithm model is trained, and the training set data is used for parameter estimation;

[0025] The trained model is used to perform trend prediction on the test set data or new unknown data. The input data is substituted into the model, and the trend values of the predicted pressure and wind speed data are calculated;

[0026] The actually collected pressure and wind speed data are input into the trained model to obtain the predicted pressure and wind speed values. According to the predicted values, the change trends of the pressure and wind speed data are analyzed, and whether there is a blockage in the air duct is judged according to the change trends.

[0027] In the fault warning module, the heartbeat packet sending rules are set. The sending frequency and format of the heartbeat packets between the range hood and the kitchen equipment are pre - agreed. The range hood and the kitchen equipment are configured with sending and receiving programs for regularly sending heartbeat packets and receiving the heartbeat packets of the other party;

[0028] The range hood and the kitchen equipment send heartbeat packets to each other and receive the heartbeat packets sent by the other party according to the established rules;

[0029] The heartbeat packet timeout time of each device is set. If the heartbeat packet of the other party is not received within the specified time, it is determined that the heartbeat packet has timed out, and the timeout judgment mechanism is triggered.

[0030] In the fault warning module, the specific contents of the top event, intermediate events, and basic events are set;

[0031] The fault tree warning model is trained using historical data to determine the occurrence probability of each basic event;

[0032] According to the occurrence probability of the basic events and the logical relationship of the fault tree, a probability calculation method is used to calculate the occurrence probabilities of each intermediate event and the top event. If the occurrence probability of the top event exceeds the pre - set threshold, it is determined that there is a fault in the communication connection between the range hood and the kitchen equipment;

[0033] According to the analysis result of the fault tree, the specific basic event or intermediate event is located, the cause of the fault is determined, and an alarm signal is output;

[0034] Feedback the cause of the fault occurrence and the processing result to the fault tree warning model, update and correct the occurrence probability of the basic event, and take corresponding handling measures according to the fault cause. After the fault handling is completed, continue the monitoring.

[0035] In the fault warning module, set the top event as the communication connection fault between the range hood and the kitchen equipment, set the intermediate events as network transmission problems, equipment hardware failures, and software program errors. Set the basic events of network transmission problems as strong electromagnetic interference nearby and insufficient network bandwidth, the basic events of equipment hardware failures as overheating of the network card and loose communication interface, and the basic events of software program errors as incompatible communication protocol versions and program memory overflow.

[0036] In the fault tree warning model, through a visualization method, draw the actual data curve and the predicted trend curve, compare and analyze the change trend of the data, find out the existing abnormal points or situations that do not meet the expectations, and further adjust and optimize the model.

[0037] In the fuzzy clustering analysis model, calculate the compactness and separation degree of the clustering to evaluate the clustering result, analyze the clustering result, and check whether it meets the expectations.

[0038] The beneficial effects of the present invention are as follows: The present invention provides a kitchen cooking linkage control system. While realizing the intelligent linkage control of kitchen equipment, through the fault tree warning model, it shows the causal relationship of system faults in a graphical way, can clearly express the logical relationship between various factors in a complex system, realizes the fault detection of the range hood, and the detection of the communication status between the range hood and the kitchen equipment, can timely discover whether there are faults, ensure the normal operation of the kitchen linkage control system, analyze the system as a whole, and provide strong support for the optimization and decision-making of the system. Brief Description of the Drawings

[0039] Figure 1 is the flowchart of the data classification of the present invention.

[0040] Figure 2 is the flowchart of the fault tree warning. Detailed Embodiment

[0041] The following will describe in detail the specific embodiments of the present invention.

[0042] Among the numerous kitchen appliances, the range hood is used frequently and has a relatively close linkage relationship with other appliances. During the cooking process, it can quickly suck in the fumes generated by the stove and discharge them outdoors through a duct, preventing the spread of fumes in the kitchen. At the same time, it can also remove the odors, water vapor, and harmful gases generated during cooking, such as carbon monoxide and nitrogen oxides, effectively improving the air quality in the kitchen. If too much fume accumulates in the kitchen, it is likely to cause a fire when encountering an open flame. The range hood timely sucks and discharges the fumes, reducing the concentration of fumes in the air, decreasing the possibility of a fire, and enhancing the safety of the kitchen. When stir-frying, the fumes can affect the line of sight. The range hood quickly sucks away the fumes, enabling the cook to see the state of the ingredients in the pot more clearly, facilitating the control of the cooking temperature and time, and improving the quality and efficiency of cooking. In an intelligent kitchen system, the range hood plays a crucial role. Since it has a linkage relationship with multiple other types of kitchen appliances, if the range hood malfunctions, it will affect the user's cooking quality. Therefore, it is necessary to monitor the range hood and the associated status between the range hood and other kitchen appliances in real time to promptly detect faults and ensure the normal operation of the kitchen system.

[0043] The connection between the range hood and other kitchen appliances includes communication connection, electrical connection, and mechanical connection. For example, in some integrated stove products, the range hood and the cooktop are mechanically connected through an integrated structural design, forming a whole in space, which helps to ensure the relative position of the range hood and the cooktop is fixed and improves the fume extraction effect. There is an electrical connection between the range hood and other kitchen appliances to achieve power supply and signal transmission. For example, the range hood and the cooktop are connected to the same power line, and through the circuit design in the electrical control box, the interlocking control between the two is realized. When the cooktop is turned on, an electrical signal is sent to the range hood through the electrical connection line to trigger the start of the range hood; after the cooktop is turned off, the range hood can also be controlled to delay turning off through the electrical connection. Communication connection is one of the important ways for the range hood to connect with other kitchen appliances in the kitchen cooking interlocking control system. For example, through wireless communication technologies such as Bluetooth and WiFi or wired communication lines, the range hood can communicate with appliances such as the cooktop, oven, and microwave oven. When the cooktop is ignited and started, a wireless signal is sent to the range hood, and the range hood automatically turns on after receiving the signal and can adjust the wind speed according to the firepower of the cooktop.

[0044] Please refer to Figures 1 to 2 As shown, the present invention provides a kitchen cooking interlocking control system, including a data acquisition module, a data classification module, a fault warning module, and a fault output module;

[0045] Data acquisition module: used to collect and integrate the data information collected by the sensor network and the data information of communication between devices;

[0046] Data classification module: Classify the data collected by the sensor network based on the fuzzy clustering analysis model and divide it into different groups;

[0047] Fault warning module: Conduct fault monitoring for different monitoring objects respectively and output warning signals;

[0048] Based on the data of the first group, use the threshold judgment algorithm to judge whether there is a fault in the motor;

[0049] Based on the data of the second group, perform consistency check on the sensor data to detect whether the sensor is faulty;

[0050] Based on the data of the third group, use the trend analysis algorithm to analyze the change trends of the pressure and wind speed data to determine whether the air duct is blocked;

[0051] Based on the data of the fourth group, based on the fault tree warning model, use the heartbeat packet mechanism to detect the communication status between devices;

[0052] Fault output module: Conduct fault alarm according to the warning signal and generate a fault detection report.

[0053] The data acquisition module uses the sensor network to acquire data. The sensor network includes a current sensor connected in series in the motor circuit of the range hood, a voltage sensor connected in parallel in the motor circuit of the range hood, a rotation speed sensor installed on the motor shaft, a smoke sensor, a pressure sensor installed in the air duct, and a wind speed sensor.

[0054] In the data classification module, the data is divided into different groups based on the fuzzy clustering analysis model. Specifically, collect the voltage, current, rotation speed, smoke, pressure, and wind speed data measured by the sensors to form a data set X = {x1, x2,..., x n}, where x i is the i-th data sample; each sample contains multiple features, such as x i = (v i , a i , r i , s i , p i , w i ), representing the voltage, current, rotation speed, smoke, pressure, and wind speed values respectively; perform normalization processing on the data to convert the data with different dimensions to the [0, 1] interval to eliminate the influence of dimensions on the clustering result. For example, for the voltage V, v' = (V - V min ) / (V max - V min ) can be used for normalization, where V min and V maxThey are the minimum and maximum values of the voltage data respectively.

[0055] Establish a fuzzy similarity matrix, process the data samples using the similarity measurement method based on Euclidean distance to obtain the Euclidean distance, convert the distance into a similarity coefficient to obtain the similarity matrix, so as to judge the similarity degree between different data samples; for example, for two data samples x i and x j , the Euclidean distance between them

[0056]

[0057] Convert the Euclidean distance into a similarity coefficient, and use to obtain the similarity matrix S=(s ij ) n×n where s ij represents the similarity degree between data samples x i and x j , and 0≤s ij ≤1.

[0058] Determine the initial membership matrix of fuzzy clustering, classify the processed data according to the similarity degree, and randomly generate an initial fuzzy membership matrix; in the present invention, the data collected by the sensor network is divided into 3 categories, which respectively correspond to the first category group as voltage, current, and rotational speed data, the second category group as smoke data, and the third category group as pressure and wind speed data, and randomly generate an initial fuzzy membership matrix U=(u ij ) n×3 , where u ij represents the membership degree of data sample x i belonging to the j-th category, satisfying 0≤u ij ≤1, and wherein, the communication data information between devices is automatically classified into the fourth category group.

[0059] Iteratively calculate the cluster centers and the membership matrix, calculate the center of each cluster according to the current membership matrix, update the membership matrix according to the new cluster centers, and repeat the above two steps until the change of the membership matrix is less than a preset threshold or the maximum number of iterations is reached. According to the current membership matrix U, calculate the center v j =(v j1 , v j2 , …, v j6 ), j = 1, 2, 2, 3, and the calculation formula is For example, for the voltage component v 11 of the cluster center of the first category (voltage, current, rotational speed), there is According to the new cluster center v j, update the membership matrix U. For each data sample x i and cluster j, its membership u ij is updated to where d ij is the distance from the data sample x i to the cluster center v j , r is a parameter greater than 1, take r = 2. Repeat the above two steps until the change in the membership matrix U is less than a pre-set threshold ε, or the maximum number of iterations is reached.

[0060] According to the final membership matrix, determine the cluster membership of each data sample. For the data sample x i , if u ij = max{u i1 , u i2 , u i3}, then x i is assigned to the j-th class. For example, if u i1 = max{u i1 , u i2 , u i3}, then x i is classified into the first class of voltage, current, and rotational speed.

[0061] Use appropriate evaluation metrics to evaluate the clustering results, such as calculating the compactness and separation of the clusters. The compactness can be measured by calculating the average distance from the data points within each cluster to the cluster center, and the separation can be measured by calculating the average distance between different cluster centers. Analyze the clustering results to check if they meet the expectations, that is, whether the voltage, current, and rotational speed data are mostly classified into one class, whether the smoke data is classified into a separate class, and whether the pressure and wind speed data are classified into one class. If the results are not satisfactory, adjust the similarity measurement method, the initial membership matrix, the number of clusters, or other parameters, and perform the clustering analysis again to ensure the accuracy of the results.

[0062] Based on the first type of data, use a threshold judgment algorithm to determine whether the motor has a fault;

[0063] The present invention determines whether the motor of the range hood is operating normally by monitoring the current, voltage, and rotational speed of the motor of the range hood, that is, a current sensor is connected in series in the circuit of the range hood motor, a voltage sensor is connected in parallel, and a rotational speed sensor is installed on the motor shaft to collect the current, voltage, and rotational speed during the operation of the motor respectively. The collected current, voltage, and rotational speed signals are subjected to mean filtering to remove high-frequency noise and obtain stable signals. Taking the current as an example, a sampling window is set, and the average value of the current data within the window is calculated as the current value at the current moment.

[0064] The threshold judgment algorithm is used to judge whether the motor has a fault. According to the rated parameters and normal operation range of the motor, the thresholds of current, voltage and speed are set. When the monitored data exceeds the threshold range, it is determined that the motor may have a fault. For example, when the motor is running normally, the current is between 2-3A. If it is detected that the current continuously exceeds 3.5A or is less than 1.5A, a fault alarm is issued.

[0065] Based on the second type of data group, the consistency check of the sensor data is carried out to detect whether the sensor is faulty;

[0066] In the present invention, redundant sensors or the consistency check of sensor data is adopted to detect whether the sensor is faulty. For example, a smoke sensor and an odor sensor are simultaneously used to detect the concentration of cooking fumes in the kitchen. By comparing whether the data collected by the two are consistent, it is judged whether the sensor is normal. If the data collected by the smoke sensor and the odor sensor are consistent, it is judged that the smoke sensor is in a normal working state. If the data collected by the two are inconsistent, it is judged that the smoke sensor is faulty.

[0067] In addition, in the kitchen linkage control system of the present invention, multiple smoke sensors are respectively set at different positions to detect the smoke concentration at different positions in the kitchen. Based on the data fusion algorithm, the data of multiple sensors are fused to obtain an accurate smoke concentration value, that is, the weighted average algorithm is adopted. Different weights are assigned to each sensor data according to the accuracy and reliability of the sensor, and then the fused cooking fume concentration value is calculated. The cooking fume concentration value obtained by calculating through the data fusion algorithm is more accurate. Specifically, assume that there are n sensors for measuring the cooking fume concentration, and the cooking fume concentration value measured by the i-th sensor is C i , and its corresponding weight is w i , and the fused cooking fume concentration value C fausion The calculation formula is:

[0068]

[0069] Based on the third type of data group, the trend analysis algorithm is adopted to analyze the change trends of the pressure and wind speed data to determine whether the air duct is blocked;

[0070] In the present invention, whether the air duct is blocked is judged by monitoring the pressure change and wind speed in the range hood air duct, that is, a pressure sensor and a wind speed sensor are installed in the air duct to monitor the pressure and wind speed conditions in the air duct in real time. The trend analysis algorithm is adopted to analyze the change trends of the pressure and wind speed data. If the pressure continuously increases and the wind speed continuously decreases within a period of time, it indicates that the air duct may be blocked. For example, a time window is set, and the change rates of the pressure and wind speed are observed within the window. If the pressure change rate is greater than a certain threshold and the wind speed change rate is less than a certain threshold, it is determined that the air duct is blocked.

[0071] First, preprocess the data collected by the sensor network, that is, preprocess the pressure values and wind speed values collected by the pressure sensor and the wind speed sensor. The preprocessing includes data cleaning and data normalization. Check whether there are missing values, outliers or incorrect data in the dataset through data cleaning. For missing values, you can choose to delete, impute (such as mean imputation, linear imputation, etc.) or use more complex machine learning methods to fill them according to the specific situation. For outliers, it is necessary to judge whether they are real data fluctuations or incorrect data caused by measurement errors, etc. If they are incorrect data, they can be considered for correction or deletion. After the data cleaning operation, normalize the pressure and wind speed data and map them to a specific interval, such as [0,1] or [-1,1], to eliminate the influence of different dimensions on data analysis and improve the convergence speed and accuracy of the algorithm.

[0072] Divide the preprocessed data or directly the classified data into a training set and a test set. Usually, most of the data is used as the training set to train the model and estimate the model parameters; a small part of the data is used as the test set to evaluate the performance and prediction accuracy of the model.

[0073] Train the selected moving average method algorithm model and use the training set data for parameter estimation. The moving average method calculates the moving average of the data and smooths the data by continuously updating the average value to highlight the long-term trend of the data. The simple moving average method takes the average value of the data within a certain time window as the trend value at the central moment of the window; the weighted moving average method assigns different weights to the data at different times, with larger weights for recent data to more sensitively reflect the change trend of the data. For example, in the moving average method, it is necessary to determine the window size of the moving average. When performing parameter estimation, the window size is determined according to the actual situation.

[0074] Use the trained model to predict the trend of the test set data or new unknown data. Substitute the input data into the model to calculate the trend values of the predicted pressure and wind speed data.

[0075] Evaluate the prediction performance of the model by calculating evaluation metrics (such as root mean square error, mean absolute percentage error, etc.). Analyze the difference between the prediction results and the actual data, and observe whether the model can accurately capture the change trends of the pressure and wind speed data, including characteristics such as rising, falling, stable and periodic. At the same time, through visualization methods, plot the actual data curve and the predicted trend curve to visually compare and analyze the change trends of the data, find possible outliers or situations that do not meet expectations, and further adjust and optimize the model.

[0076] Input the actually collected pressure and wind speed data into the trained model to obtain the predicted pressure and wind speed values. Analyze the change trends of the pressure and wind speed data based on the predicted values, and judge whether there is a blockage in the air duct according to the change trends.

[0077] Based on the fourth category of data, based on the fault tree warning model, adopt the heartbeat packet mechanism to detect the communication status between devices.

[0078] In the present invention, the communication connection failure between the range hood and other kitchen appliances is taken as an example for illustration.

[0079] Set the heartbeat packet sending rules, and pre-agree on the sending frequency and format of the heartbeat packets between the range hood and kitchen appliances (such as cooktops, dishwashers, microwave ovens, etc.). The range hood and kitchen appliances are configured with sending and receiving programs to regularly send heartbeat packets and receive the heartbeat packets of the other party. For example, it can be set to send a heartbeat packet every 5 seconds. The heartbeat packet adopts a simple text format, including the unique identifier and timestamp of the device, such as "DeviceID:001,Timestamp:2025-03-25 12:00:00".

[0080] The range hood and kitchen appliances regularly send heartbeat packets to the other party and receive the heartbeat packets sent by the other party according to the established rules.

[0081] Set the heartbeat packet timeout time for each device. If the heartbeat packet of the other party is not received within the specified time, it is determined that the heartbeat packet has timed out, and the timeout judgment mechanism is triggered. For example, the timeout time is set to 10 seconds. When a device does not receive the heartbeat packet of the other party within 10 seconds, the timeout judgment mechanism is triggered.

[0082] Set the specific contents of the top event, intermediate events, and basic events.

[0083] Use logic gates to represent the logical relationships between the top event, intermediate events, and basic events. For example, the three intermediate events of network transmission problems, device hardware failures, and software program errors are connected to the top event through an OR gate, meaning that as long as any one of these intermediate events occurs, it may cause the top event to occur. Strong electromagnetic interference nearby and insufficient network bandwidth are connected to the network transmission problem through an OR gate, meaning that as long as any one of these basic events occurs, it may cause the intermediate event to occur.

[0084] Use historical data to train the fault tree warning model to determine the occurrence probability of each basic event.

[0085] According to the occurrence probability of basic events and the logical relationship of the fault tree, using probability calculation methods, calculate the occurrence probabilities of each intermediate event and the top event. If the occurrence probability of the top event exceeds a pre-set threshold, it is determined that there is a fault in the communication connection between the range hood and the kitchen equipment.

[0086] According to the analysis results of the fault tree, locate the specific basic event or intermediate event, determine the cause of the fault, and output an alarm signal. For example, if it is calculated that the occurrence probability of network transmission problems is relatively high and the occurrence probability of the basic event of strong electromagnetic interference nearby is also relatively large, it can be determined that the strong electromagnetic interference causes the communication fault.

[0087] In the fault warning module, set the top event as the communication connection fault between the range hood and the kitchen equipment, and set the intermediate events as network transmission problems, equipment hardware failures, and software program errors. Set the basic events of network transmission problems as strong electromagnetic interference nearby and insufficient network bandwidth. The basic events of equipment hardware failures are overheating of the network card and loose communication interface. The basic events of software program errors are incompatible communication protocol versions and program memory overflow.

[0088] Feed back the cause of the fault and the processing result to the fault tree warning model, update and correct the occurrence probability of the basic event, improve the accuracy and reliability of the fault tree warning model, and take corresponding processing measures according to the cause of the fault. After the fault is processed, continue to monitor to ensure that the fault is completely resolved.

[0089] The present invention classifies the data collected by the sensor network based on the fuzzy clustering analysis model. For example, voltage, current, and rotation speed data are the first group, used to determine whether the motor of the range hood is faulty; smoke data is the second group, and by performing consistency checks on the data of multiple sensors, it is determined whether the smoke sensor is faulty. And multiple smoke sensors are respectively set at different positions in the kitchen to measure the oil fume concentration. Based on the data fusion algorithm, the data of multiple sensors are fused to obtain an accurate smoke concentration value; pressure and wind speed data are the third group, and the trend analysis algorithm is used to analyze the change trend of the pressure and wind speed data, and based on this, it is analyzed whether there is a blockage in the air duct. Based on the fault tree warning model, combined with the heartbeat packet mechanism, the communication status between the range hood and other kitchen equipment is detected. If there is a fault, the fault point can be found in time and the cause of the fault can be analyzed, and a fault report can be generated for easy viewing later to ensure that normal communication can be carried out between the equipment, so as to ensure the normal operation of the entire kitchen cooking linkage control system.

[0090] The above embodiments are only descriptions of the preferred embodiments of the present invention, and do not limit the scope of the present invention. Without departing from the design spirit of the present invention, various deformations and improvements made by those of ordinary skill in the art to the technical solutions of the present invention shall fall within the protection scope determined by the claims of the present invention.

Claims

1. A kitchen cooking linkage control system, characterized in that, Including: A data acquisition module, a data classification module, a fault warning module, and a fault output module; The data acquisition module: used to collect and integrate the data information collected by the sensor network and the data information of the communication between devices; The data classification module: classifies the data collected by the sensor network based on the fuzzy clustering analysis model and divides it into different groups; The fault warning module: performs fault monitoring for different monitoring objects respectively and outputs a warning signal; Based on the data of the first group, use the threshold judgment algorithm to judge whether the motor has a fault; Based on the data of the second group, perform consistency check on the sensor data to detect whether the sensor has a fault; Based on the data of the third group, use the trend analysis algorithm to analyze the change trend of the pressure and wind speed data to determine whether the air duct is blocked; Based on the data of the fourth group, based on the fault tree warning model, use the heartbeat packet mechanism to detect the communication status between devices; The fault output module: performs fault alarm according to the warning signal and generates a fault detection report.

2. The kitchen cooking linkage control system according to claim 1, characterized in that, The data acquisition module uses the sensor network to collect data. The sensor network includes a current sensor connected in series in the motor circuit of the range hood, a voltage sensor connected in parallel in the motor circuit of the range hood, a speed sensor installed on the motor shaft, a smoke sensor, a pressure sensor and a wind speed sensor installed in the air duct.

3. The kitchen cooking linkage control system according to claim 1, characterized in that In the data classification module, the data is divided into different groups based on the fuzzy clustering analysis model. The specific steps include: Collect the voltage, current, speed, smoke, pressure and wind speed data measured by the sensors to form a data set; Perform normalization processing on the data; Establish a fuzzy similarity matrix, use the similarity measurement method based on the Euclidean distance to process the data samples, obtain the Euclidean distance, convert the distance into a similarity coefficient, obtain the similarity matrix, and judge the similarity degree between different data samples; Determine the initial membership matrix of fuzzy clustering, classify the processed data according to the similarity degree, and randomly generate an initial fuzzy membership matrix; Iteratively calculate the cluster center and the membership matrix. According to the current membership matrix, calculate the center of each cluster. According to the new cluster center, update the membership matrix. Repeat the above two steps until the change of the membership matrix is less than a pre-set threshold or the maximum number of iterations is reached; According to the final membership matrix, determine the cluster belonging of each data sample.

4. The kitchen cooking linkage control system according to claim 1, characterized in that, In the fault warning module, perform mean filtering on the collected current, voltage and speed signals, use the threshold judgment algorithm to judge whether the motor has a fault, set the thresholds of current, voltage and speed according to the rated parameters and normal operating range of the motor, and when the monitored data exceeds the threshold range, it is determined that the motor has a fault.

5. The kitchen cooking linkage control system according to claim 1, characterized in that, In the fault warning module, divide the classified data of the third group into a training set and a test set; Train the selected moving average method algorithm model and use the training set data for parameter estimation; Use the trained model to perform trend prediction on the test set data or new unknown data. Substitute the input data into the model to calculate the trend values of the predicted pressure and wind speed data; Input the actually collected pressure and wind speed data into the trained model to obtain the predicted pressure and wind speed values. Analyze the change trends of the pressure and wind speed data based on the predicted values, and determine whether there is a blockage in the air duct according to the change trends.

6. The kitchen cooking linkage control system according to claim 1, wherein, In the fault warning module, set the heartbeat packet sending rules, and pre - agree on the sending frequency and format of the heartbeat packets between the range hood and the kitchen equipment. The range hood and the kitchen equipment are configured with sending and receiving programs to regularly send heartbeat packets and receive the heartbeat packets from each other. The range hood and the kitchen equipment send heartbeat packets to each other regularly according to the established rules and receive the heartbeat packets sent by the other party. Set the heartbeat packet timeout time for each device. If the heartbeat packet from the other party is not received within the specified time, it is determined that the heartbeat packet has timed out, and the timeout judgment mechanism is triggered.

7. The kitchen cooking linkage control system according to claim 6, wherein In the fault warning module, set the specific contents of the top event, intermediate events, and basic events. Use logic gates to represent the logical relationships between the top event, intermediate events, and basic events. Use historical data to train the fault tree warning model to determine the occurrence probability of each basic event. According to the occurrence probability of the basic events and the logical relationship of the fault tree, use probability calculation methods to calculate the occurrence probabilities of each intermediate event and the top event. If the occurrence probability of the top event exceeds the pre - set threshold, it is determined that there is a fault in the communication connection between the range hood and the kitchen equipment. According to the analysis results of the fault tree, locate the specific basic event or intermediate event, determine the cause of the fault, and output an alarm signal. Feed back the cause of the fault and the processing result to the fault tree warning model to update and correct the occurrence probability of the basic events, and take corresponding treatment measures for the cause of the fault. After the fault is processed, continue the monitoring.

8. The kitchen cooking linkage control system according to claim 7, wherein In the fault warning module, set the top event as the communication connection fault between the range hood and the kitchen equipment, and set the intermediate events as network transmission problems, equipment hardware failures, and software program errors. Set the basic events of network transmission problems as the existence of strong electromagnetic interference nearby and insufficient network bandwidth, the basic events of equipment hardware failures as overheating of the network card and loose communication interfaces, and the basic events of software program errors as incompatible communication protocol versions and program memory overflow.

9. The kitchen cooking linkage control system according to claim 8, wherein, In the fault tree warning model, through visualization methods, draw the actual data curve and the predicted trend curve, compare and analyze the change trends of the data, find out the existing abnormal points or situations that do not meet the expectations, and further adjust and optimize the model.

10. The kitchen cooking linkage control system according to claim 3, characterized in that, In the fuzzy clustering analysis model, calculate the compactness and separation degree of the clustering to evaluate the clustering results, analyze the clustering results, and check whether they meet the expectations.

Images