Intelligent control method and system for waterproof electric heating kettle

Abstract

The invention discloses an intelligent control method and system for a waterproof electric heating kettle, and relates to the technical field of intelligent temperature control, the heating duration when the electric heating kettle completes a heating task is predicted and obtained, if the prediction result does not reach the expectation, a control strategy library outputs a control strategy of the electric heating kettle, the control strategy is tested, and the electric heating kettle is started. If the effectiveness of the control strategy is insufficient, optimizing various parameters of the control strategy; the method comprises the following steps: establishing an error degree according to an error data difference when an electric heating pot executes a heating task, establishing alarm intensity according to a time node when the error degree exceeds an expected value, if the alarm intensity exceeds the expected value, constraining maintenance frequency in a current stage according to the alarm intensity, and giving a maintenance scheme for the electric heating pot by an operation fault maintenance knowledge graph. And executing the maintenance scheme to maintain the electric heating kettle. Maintenance measures are introduced after the electric heating kettle is determined to be in the fault state, and normal operation of the electric heating kettle is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent temperature control, and in particular to an intelligent control method and system for a waterproof electric heating pot. Background Art

[0002] Intelligent temperature control is a highly integrated advanced technology that cleverly combines high-precision temperature sensors, intelligent microprocessors, and efficient actuators. By sensing changes in ambient temperature or internal temperature of the device in real time, the system can respond quickly and automatically adjust the heating or cooling power to ensure that the temperature is accurately maintained within the preset ideal range. This intelligent adjustment not only greatly improves the accuracy and response speed of temperature control, but also effectively reduces energy consumption and extends the service life of the equipment. At the same time, it also brings users a more convenient and efficient control experience, making temperature control more intelligent and humane.

[0003] In the Chinese invention patent with application publication number CN117170433A, a temperature intelligent control method and system based on linkage control are disclosed, including: obtaining storage temperature range and distribution temperature range; obtaining cold chain system nodes and collecting real-time temperature data; using wireless transmission technology to synchronize real-time temperature data to the linkage control center and draw a product temperature fluctuation curve; obtaining extensive control information; calculating the optimal storage temperature range and the optimal distribution temperature range, and obtaining refined control information; performing temperature intelligent control to solve the technical problems that fixed rules and static parameters cannot flexibly respond to different environmental conditions and cannot effectively control temperature in complex application scenarios, and realize dynamic adjustment according to scenario requirements, respond to temperature changes more quickly, reduce product temperature fluctuations, and maintain stable temperature under storage and distribution conditions.

[0004] Combined with the above application and the contents of the prior art:

[0005] When an electric heating pot performs a heating task, such as boiling water, after the target temperature for heating is set in advance, it is usually necessary to precisely control the heating process. In particular, when a roughly constant temperature state needs to be maintained, the temperature control of the heating process needs to be more detailed and precise.

[0006] In the existing temperature control method for electric heating pots, after determining the target temperature for heating, the estimated heating time is usually determined based on linear regression, the estimated heating time is displayed, and the heating element is restarted when the temperature drops to heat again; however, if it is necessary to reach the target temperature within a specific time, especially when the electric heating pot is in a humid environment, the conductivity and thermal efficiency of the heating element of the electric heating pot will be affected to a certain extent. Therefore, the difficulty of temperature control of the electric heating pot will be further increased. At the same time, since it is difficult to achieve dynamic control of the heating element, the heating accuracy of the electric heating element will be further affected, and the heating task cannot be completed continuously and effectively.

[0007] To this end, the present invention provides an intelligent control method and system for a waterproof electric heating pot. Summary of the invention

[0008] 1. Technical issues to be resolved

[0009] In view of the deficiencies of the prior art, the present invention provides an intelligent control method and system for waterproof electric heating pots. By testing the control strategy, if the effectiveness of the control strategy is insufficient, the various parameters of the control strategy are optimized; the error degree is constructed by the error data difference when the electric heating pot performs the heating task, and the alarm density is constructed according to the time node when the error degree exceeds the expectation. If the alarm density exceeds the expectation, the maintenance frequency in the current stage is constrained according to the alarm density, and a maintenance plan is given for the electric heating pot by the operation fault maintenance knowledge map, and the maintenance plan is executed to maintain the electric heating pot. By introducing maintenance measures after the electric heating pot is determined to be in a fault state, the normal operation of the electric heating pot is achieved, thereby solving the technical problems recorded in the background technology.

[0010] (II) Technical solution

[0011] To achieve the above objectives, the present invention is implemented through the following technical solutions:

[0012] An intelligent control method for a waterproof electric heating pot, comprising: constructing a humidity value Sot at each collection point from the recorded humidity data in the working area, clustering a number of collection points, selecting a target area in the working area for the electric heating pot to operate, and recording the humidity data at the collection points in the target area;

[0013] Conduct usage tests on the electric heating pot under different simulated humid conditions, obtain the operation data of the electric heating pot, and predict the heating time when the electric heating pot completes the heating task. If the prediction result does not meet expectations, issue adjustment instructions to the outside;

[0014] After the control strategy library outputs the control strategy of the electric heating pot, the control strategy is tested. If the control strategy is not effective enough, various parameters of the control strategy are optimized to obtain the optimized control strategy.

[0015] The error degree Qts is constructed by the error data difference when the electric heating pot performs the heating task, and the alarm density Moj is constructed according to the time node when the error degree Qts exceeds the expected value. If the alarm density Moj exceeds the warning threshold, a maintenance instruction is issued to the outside.

[0016] The maintenance frequency in the current stage is constrained according to the alarm density. At the maintenance node that meets the constraints, the operation fault maintenance knowledge graph provides a maintenance plan for the electric heating pot, and the maintenance plan is executed to maintain the electric heating pot.

[0017] Furthermore, an electronic map covering the working area is constructed, and each collection point is marked on the electronic map; air humidity data is periodically monitored and collected at each collection point and then summarized to generate a humidity data set; and the humidity value Sot at the collection point is constructed from the humidity data set.

[0018] Furthermore, the air humidity Ks is linearly normalized, and the corresponding data value is mapped to the interval [0,1], and the humidity value Sot is constructed as follows:

[0019]

[0020] Where i = 1, 2, ..., n, n is the number of acquisitions, weight coefficient: 0 ≤ F1 ≤ 1, 0 ≤ F2 ≤ 1, and F1 + F2 = 1; Ks i is the air humidity collected for the i-th time, Ks a is the mean value of air humidity, Ks b is the acceptable value of air humidity;

[0021] Furthermore, the collection points are marked with the obtained humidity values; a pre-trained clustering algorithm is used to cluster several collection points, and the working area is divided into several sub-areas; the average value of the humidity values ​​Sot at several collection points in the sub-area is calculated, and the sub-area with the lowest average humidity value is taken as the target area.

[0022] Furthermore, based on the humidity data in the target area, a humidity condition simulation is performed in a laboratory environment, and the electric heating cooker is tested for use under different simulated humidity conditions to obtain the operation data of the electric heating cooker, and the test operation data set is generated by summarizing;

[0023] The target heating time is pre-set, and when the electric heating pot is operated under humid conditions, the heating state data, the operation data of the heating element and the humidity data in the target area are recorded.

[0024] Further, using the heating state data and environmental condition data of the electric heating pot as inputs, predict the estimated heating duration when the electric heating pot completes the heating task by the trained heating prediction model. If the estimated heating duration is inconsistent with the target heating duration, send an adjustment instruction to the outside.

[0025] Further, after receiving the adjustment instruction, summarize a number of pre-constructed control strategies to build a control strategy library for the heating element; using the heating state data of the electric heating pot and the operating data of the heating element as inputs, output corresponding control strategies for the heating element by the control strategy library.

[0026] Further, test the control strategy of the electric heating pot by the trained heating prediction model to obtain the estimated heating duration when the heating task is completed. If the estimated heating duration is still inconsistent with the target heating duration, send an optimization instruction to the outside;

[0027] Execute the optimized control strategy to control the electric heating pot, and collect the operating data of the electric heating pot, and summarize and build a set of electric heating pot operating data.

[0028] Further, record the time difference between the preset heating duration and the estimated duration each time the heating task is executed, and construct an error degree Qts from the obtained time difference Ct. If the error degree Qts exceeds the error threshold, send an alarm instruction to the outside;

[0029] After receiving several alarm instructions continuously, record the time nodes when the alarm instructions are received within the most recent usage stage, and use them as alarm nodes. Construct an alarm density Moj based on the alarm nodes. If the alarm density Moj exceeds the warning threshold, send a maintenance instruction to the outside.

[0030] Further, the method for constructing the alarm density Moj is as follows:

[0031]

[0032] Where: d ij <D, e takes the value of 2.718, weight coefficient, 0 ≤ F1 ≤ 1, 0 ≤ F2 ≤ 1, and F1 + F2 = 1, D is the radius of the usage stage; p i The weighted value of the i-th alarm instruction, which is the time interval from the i-th alarm instruction to the j-th alarm instruction, and n is the number of alarm nodes.

[0033] Further, perform linear normalization on the time difference Ct, map the corresponding data values to the interval [0, 1], and construct the error degree Qts in the following manner:

[0034]

[0035] Where i = 1, 2, ..., n, n is the number of acquisitions, weight coefficient: 0 ≤ F1 ≤ 1, 0 ≤ F2 ≤ 1, and F1 + F2 = 1; Ct i is the time difference of the i-th use, Ct a is the mean of the time difference, Ct b is the acceptable value of the duration difference;

[0036] Furthermore, after receiving the maintenance instruction, a maintenance cycle including several maintenance nodes is pre-set, and the maintenance frequency in the current stage is constrained according to the alarm density, and the electric heating pot is maintained at the maintenance nodes that meet the constraint conditions;

[0037] The operation data of the electric heating pot is collected, and features are extracted from the acquired operation data to obtain corresponding maintenance features. The electric heating pot fault maintenance is used as the target word, and the operation fault maintenance knowledge graph of the electric heating pot is pre-built.

[0038] An intelligent control system for a waterproof electric heating pot, comprising: a humidity analysis unit, which constructs a humidity value Sot at each collection point from the recorded humidity data in a working area, performs clustering processing on a number of collection points, selects a target area in the working area for the electric heating pot to operate, and records the humidity data at the collection points in the target area;

[0039] The heating prediction unit tests the electric heating pot under different simulated humid conditions, obtains the operation data of the electric heating pot, and predicts the heating time when the electric heating pot completes the heating task. If the prediction result does not meet the expectation, an adjustment instruction is issued to the outside.

[0040] The strategy dynamic control unit tests the control strategy of the electric heating pot after the control strategy library outputs the control strategy. If the control strategy is not effective enough, the parameters of the control strategy are optimized to obtain the optimized control strategy.

[0041] The error alarm unit constructs the error degree Qts from the error data difference when the electric heating pot performs the heating task, and constructs the alarm density Moj according to the time node when the error degree Qts exceeds the expected time node. If the alarm density Moj exceeds the warning threshold, a maintenance instruction is issued to the outside;

[0042] The fault maintenance unit constrains the maintenance frequency in the current stage according to the alarm density. At the maintenance node that meets the constraints, the fault maintenance knowledge graph is used to provide a maintenance plan for the electric heating pot, and the maintenance plan is executed to maintain the electric heating pot.

[0043] (III) Beneficial effects

[0044] The present invention provides an intelligent control method and system for a waterproof electric heating pot, which has the following beneficial effects:

[0045] 1. Evaluate and judge the environmental humidity in the working area based on the humidity value Sot to determine whether the current humid environment is suitable for the use of the electric heating cooker. If it is not suitable, targeted treatment can be carried out. Select the target area in the working area based on the position distribution of each humidity value Sot. After placing the electric heating cooker in the target area, the impact of the humid environment on the electric heating cooker can be reduced, so that the electric heating cooker can perform the heating task with higher accuracy.

[0046] 2. After collecting the electric heating pot and related data, the heating process of the electric heating pot is predicted in real time, the time required for the electric heating pot to complete the heating task is understood in real time, and the working state of the electric heating pot is adjusted in real time. By dynamically optimizing and adjusting the matched control strategy, the heating element is dynamically adjusted and optimized, and the heating element is continuously dynamically adjusted according to the prediction results, the working accuracy of the electric heating pot can be improved, and when the electric heating pot is running in a humid environment, the interference of environmental conditions on the electric heating pot can be reduced.

[0047] 3. By counting whether the electric heating pot effectively completes the heating task each time, the error degree Qts is constructed. Based on the error degree Qts, the reliability of the electric heating pot can be comprehensively evaluated, and an alarm command can be issued in time when the task cannot be completed for multiple times, introducing external intervention.

[0048] 4. Evaluate the use risk of the electric heating cooker based on the alarm density Moj. When the electric heating cooker issues an alarm command several times in a row, judge the fault state of the electric heating cooker. After determining that the electric heating cooker is in a fault state, introduce maintenance measures to achieve normal operation of the electric heating cooker on the basis of dynamic control of the electric heating cooker.

[0049] 5. By restricting the maintenance frequency, the maintenance frequency is adapted to the degree of failure of the electric heating pot, avoiding excessive overhaul and maintenance, too many invalid maintenance times, or difficulty in timely maintenance, which may cause the electric heating pot to fail to operate normally.

[0050] 6. On the basis of dynamic adjustment and optimization of the temperature control strategy, if the electric heating pot is affected by the humid environment and an operational failure occurs, the operational failure maintenance knowledge graph will provide a maintenance plan for the electric heating pot. When the electric heating pot needs maintenance, targeted maintenance can be achieved and the operating status of the electric heating pot can be adjusted. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 It is a schematic flow chart of the intelligent control method of the waterproof electric heating pot of the present invention;

[0052] Figure 2 It is a schematic flow chart of the intelligent control method of the waterproof electric heating pot of the present invention. DETAILED DESCRIPTION

[0053] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0054] See also Figure 1 The present invention provides an intelligent control method for a waterproof electric heating pot, comprising:

[0055] Step 1: construct the humidity value Sot at each collection point from the recorded humidity data in the working area, perform clustering on several collection points, select a target area in the working area where the power supply heating pot is running, and record the humidity data at the collection points in the target area;

[0056] The step 1 includes the following contents:

[0057] Step 101: after determining the working area of ​​the electric heating cooker, construct an electronic map covering the working area, set a number of collection points in the working area, and mark each collection point on the electronic map; after periodically monitoring and collecting air humidity data at each collection point, aggregate the acquired humidity data to generate a humidity data set;

[0058] Step 102: construct the humidity value Sot at each collection point from the humidity data in the humidity data set, and mark the collection point with the obtained humidity value, wherein the air humidity Ks is linearly normalized and the corresponding data value is mapped to the interval [0,1] in the following manner:

[0059]

[0060] Where i = 1, 2, ..., n, n is the number of acquisitions, weight coefficient: 0 ≤ F1 ≤ 1, 0 ≤ F2 ≤ 1, and F1 + F2 = 1; weight coefficient is determined by reference to the hierarchical analysis method; Ks i is the air humidity collected for the i-th time, Ks a is the mean value of air humidity, Ks b is the acceptable value of air humidity;

[0061] When in use, after determining the working area of ​​the electric heating cooker, by monitoring and collecting humidity data in the working area and constructing a humidity value Sot, the environmental humidity conditions in the working area are evaluated and judged according to the humidity value Sot, so as to determine whether the current humid environment is suitable for the use of the electric heating cooker. If it is not suitable for use, the working area can be dehumidified, or the waterproof and moisture-proof performance of the electric heating cooker can be specifically increased;

[0062] Step 103: clustering the plurality of collection points using a pre-trained clustering algorithm, dividing the working area into a plurality of sub-areas; calculating the average value of humidity values ​​Sot at the plurality of collection points in the sub-areas, taking the sub-area with the lowest average humidity value as the target area, and recording the humidity data at the collection points in the target area;

[0063] When using, combine the contents in steps 101 to 103:

[0064] After obtaining the humidity value Sot in each sub-area, the target area is screened out in the working area according to the position distribution of each humidity value Sot. After the electric heating cooker is placed in the target area, the impact of the humid environment on the electric heating cooker can be reduced, so that the electric heating cooker can be more accurate when performing heating tasks.

[0065] In the existing temperature control method for electric heating pots, after determining the target temperature for heating, the estimated heating time is usually determined based on linear regression, the estimated heating time is displayed, and the heating element is restarted when the temperature drops to heat again; however, if it is necessary to reach the target temperature within a specific time, especially when the electric heating pot is in a humid environment, the conductivity and thermal efficiency of the heating element of the electric heating pot will be affected to a certain extent. Therefore, the difficulty of temperature control of the electric heating pot will be further increased. At the same time, since it is difficult to achieve dynamic control of the heating element, the heating accuracy of the electric heating element will be further affected, and the heating task cannot be completed continuously and effectively.

[0066] Step 2: Perform a usage test on the electric heating pot under different simulated humid conditions to obtain the operation data of the electric heating pot, and predict the heating time when the electric heating pot completes the heating task. If the prediction result does not meet the expectation, issue an adjustment instruction to the outside;

[0067] The step 2 includes the following contents:

[0068] Step 201: Based on the humidity data in the target area, a humidity condition simulation is performed in a laboratory environment to obtain several sets of simulated humidity conditions, and the electric heating cooker is tested under different simulated humidity conditions to obtain the operation data of the electric heating cooker, which is then aggregated to generate a test operation data set of the electric heating cooker;

[0069] Step 202: pre-set a target heating time, and when the electric heating pot is operated under humid conditions, record heating state data, operating data of the heating element, and humidity data in the target area; use the operating data and operating environment data of the electric heating pot as sample data, use the sample data to train a convolutional neural network, and obtain a trained heating prediction model;

[0070] Step 203: Taking the heating state data and environmental condition data of the electric heating pot as input, the trained heating prediction model predicts the estimated heating time when the electric heating pot completes the heating task. If the estimated heating time is inconsistent with the target heating time, it means that the control accuracy of the electric heating pot is insufficient. At this time, an adjustment instruction is issued to the outside.

[0071] When used, the contents in steps 201 to 203 are combined:

[0072] After collecting and recording several items of data as sample data, the heating prediction model is trained and acquired. Thus, after collecting the electric heating pot and related data, the heating process of the electric heating pot can be predicted in real time, and the time required for the electric heating pot to complete the heating task can be understood in real time. The working state of the electric heating pot can be adjusted in real time according to the prediction results.

[0073] Step 3: After the control strategy library outputs the control strategy of the electric heating pot, the control strategy is tested. If the control strategy is not effective enough, various parameters of the control strategy are optimized to obtain the optimized control strategy.

[0074] The step three includes the following contents:

[0075] Step 301: after receiving the adjustment instruction, a plurality of pre-built control strategies are aggregated to build a control strategy library of the heating element; the heating state data of the electric heating pot and the operation data of the heating element are used as input, and the control strategy library outputs the corresponding control strategy for the heating element;

[0076] When in use, the working parameters of the heating element can be adjusted according to the current heating temperature and the expected heating time, so that the electric heating pot can complete the heating task within the target heating time;

[0077] Step 302: Under the current humidity environment in the target area, the control strategy of the electric heating pot is tested by the trained heating prediction model to obtain the estimated heating time when the heating task is completed. If the estimated heating time is still inconsistent with the target heating time, it means that the current control strategy is not feasible enough and needs to be optimized, and an optimization instruction is issued to the outside.

[0078] When in use, by comparing the preset estimated heating time with the target heating time, the operating reliability of the electric heating pot can be evaluated based on the difference between the two. If the difference between the two is larger, the reliability is lower, and the current control strategy needs to be adjusted;

[0079] Step 303: after receiving the optimization instruction, use a multi-objective optimization algorithm to optimize various parameters of the control strategy to obtain an optimized control strategy; execute the optimized control strategy to control the electric heating pot, collect the operation data of the electric heating pot, and summarize and construct an electric heating pot operation data set;

[0080] When used, combine the contents in steps 301 and 302:

[0081] By dynamically optimizing and adjusting the matched control strategy, the heating element can be dynamically adjusted and optimized. By continuously dynamically adjusting the heating element based on the prediction results, the working accuracy of the electric heating pot can be improved. When the electric heating pot is operating in a humid environment, the interference of environmental conditions on the electric heating pot can be reduced.

[0082] Step 4: construct the error degree Qts from the error data difference when the electric heating pot performs the heating task, and construct the alarm density Moj according to the time node when the error degree Qts exceeds the expected time node. If the alarm density Moj exceeds the warning threshold, issue a maintenance instruction to the outside;

[0083] The step 4 includes the following contents:

[0084] Step 401: After the electric heating pot has been used continuously, within a preset observation period, the time difference between the preset heating time and the expected time is recorded each time a heating task is performed, and the error degree Qts is constructed based on the obtained time difference Ct, so that the difference between the heating time and the expected time can be judged based on the error degree;

[0085] The error degree is constructed as follows: linear normalization is performed on the time difference Ct, and the corresponding data values ​​are mapped to the interval [0,1] according to the following method:

[0086]

[0087] Where i = 1, 2, ..., n, n is the number of acquisitions, weight coefficient: 0 ≤ F1 ≤ 1, 0 ≤ F2 ≤ 1, and F1 + F2 = 1; the value of the weight coefficient is consistent with the previous value; Ct i is the time difference of the i-th use, Ct a is the mean of the time difference, Ct b is the acceptable value of the duration difference;

[0088] Set an error threshold in advance based on historical data and the management expectations for heating errors; if the error degree Qts exceeds the error threshold, it indicates that there may be certain deficiencies in the heating accuracy of the electric heating pot, and targeted treatment is required for this lack of accuracy. At this time, send an alarm instruction to the outside;

[0089] During use, on the basis of the electric heating pot being used continuously for several times, construct the error degree Qts by counting whether the electric heating pot effectively completes the heating task each time. Based on the error degree Qts, the reliability of the electric heating pot can be comprehensively evaluated, and an alarm instruction can be sent in a timely manner when the work task cannot be completed multiple times to introduce external intervention.

[0090] Step 402: After receiving several alarm instructions continuously, record the time nodes when the alarm instructions are received during the most recent usage stage and use them as alarm nodes. Under dimensionless conditions, construct the alarm density Moj based on the alarm nodes as follows:

[0091]

[0092] In the formula: d ij <D, e takes the value of 2.718, weight coefficient, 0 ≤ F1 ≤ 1, 0 ≤ F2 ≤ 1, and F1 + F2 = 1. The value of the weight coefficient remains the same as the previous value; D is the radius of the usage stage; p i is the weighted value of the i-th alarm instruction, and the weighted value falls within [0.1, 0.5], and the weighted value is positively correlated with the error degree Qts; d ij is the time interval from the i-th alarm instruction to the j-th alarm instruction, and n is the number of alarm nodes.

[0093] Set a warning threshold in advance based on historical data and the usage management expectations for the electric heating pot;

[0094] If the alarm density Moj exceeds the warning threshold, it indicates that when the electric heating pot is running, it cannot continuously and effectively complete the heating task, and the risk of operating failures during the current operating stage is relatively high. Maintenance needs to be carried out in a timely manner or in advance. At this time, send a maintenance instruction to the outside;

[0095] During use, combine the content in steps 401 and 402:

[0096] In the scenario where several alarm instructions are received continuously, an alarm density Moj is constructed. Based on the alarm density Moj, the use risk of the electric heating cooker can be evaluated. When the electric heating cooker sends out alarm instructions several times continuously, it means that the control of the electric heating cooker has failed or it is difficult to achieve the corresponding effect. Therefore, the fault state of the electric heating cooker can be judged. After the electric heating cooker is determined to be in a fault state, maintenance measures are introduced to achieve normal operation of the electric heating cooker on the basis of dynamic control of the electric heating cooker.

[0097] Step 5: Constrain the maintenance frequency in the current stage according to the alarm density. At the maintenance node that meets the constraint conditions, the operation fault maintenance knowledge graph provides a maintenance plan for the electric heating pot, and executes the maintenance plan to maintain the electric heating pot;

[0098] The step five includes the following contents:

[0099] Step 501: After receiving the maintenance instruction, a maintenance cycle including several maintenance nodes is pre-set. Under dimensionless conditions, the maintenance frequency in the current stage is constrained according to the alarm density, and the electric heating pot is maintained at the maintenance node that meets the constraint conditions. The maintenance frequency constraint method is as follows:

[0100]

[0101] Weight coefficient, 0≤F1≤1, 0≤F2≤1, and F1+F2=1; the value of the weight coefficient is consistent with the previous value; where p is the number of maintenance times within the maintenance cycle, X ij is the time interval from the ith maintenance to the jth maintenance, X a is the average value of the time interval, and Moj is the alarm density.

[0102] During use, when the electric heating pot needs maintenance, the maintenance frequency is restricted so that the maintenance frequency is adapted to the degree of failure of the electric heating pot, thereby avoiding excessive overhaul and maintenance, too many ineffective maintenance times, or difficulty in timely maintenance, which may cause the electric heating pot to fail to operate normally.

[0103] Step 502: collect the operation data of the electric heating cooker, extract features from the acquired operation data and obtain corresponding maintenance features; take the fault maintenance of the electric heating cooker as the target word, and after deep retrieval and entity relationship building, pre-build the operation fault maintenance knowledge graph of the electric heating cooker;

[0104] According to the correspondence between maintenance characteristics and operation maintenance plans, the operation fault maintenance knowledge graph provides a maintenance plan for the electric heating pot, and the maintenance plan is executed to maintain the electric heating.

[0105] When using, combine the contents in steps 501 and 502:

[0106] When the electric heating pot needs maintenance, on the basis of dynamically adjusting and optimizing the temperature control strategy, if the electric heating pot is affected by the humid environment and an operational failure occurs, the operational failure maintenance knowledge graph will provide a maintenance plan for the electric heating pot. When the electric heating pot needs maintenance, targeted maintenance can be implemented and the operating status of the electric heating pot can be adjusted.

[0107] The Analytic Hierarchy Process (AHP) is a decision-making method that decomposes decision-related elements into levels such as goals, criteria, and plans, and conducts qualitative and quantitative analysis on this basis. It is particularly suitable for dealing with target systems with hierarchical and staggered evaluation indicators, and when the target value is difficult to describe quantitatively, the AHP is an effective decision-making tool.

[0108] The core of the hierarchical analysis method is to decompose the decision problem into multiple levels to form a hierarchical structure, which usually includes the target level, the criterion level, the sub-criterion level and the solution level. By solving the eigenvector of the judgment matrix, the priority weight of each element of each level to an element of the previous level is obtained, and the final weight of each alternative solution to the total goal is recursively merged by the weighted sum method, so as to find the optimal solution.

[0109] First, it is necessary to clarify the construction goal of the knowledge graph of electric heating pot operation fault maintenance, that is, to build a knowledge system that can comprehensively reflect the common faults, fault causes, fault phenomena, troubleshooting steps and solutions of electric heating pots. At the same time, determine the coverage of the knowledge graph, including but not limited to power failure, heating failure, control failure, etc.

[0110] Fault case collection: Fault cases are collected from multiple channels such as electric heating cooker manufacturers, maintenance stations, and user feedback, including fault descriptions, phenomena, and solution processes. Technical document compilation: Official documents such as the user manual, maintenance manual, and technical specifications of electric heating cookers are compiled to extract troubleshooting and maintenance guidance information. Expert interviews: Experts in the field of electric heating cookers are invited to interview and obtain their experience and insights in actual maintenance.

[0111] Entity extraction: Identify key entities from the collected data, such as fault type (power failure, heating failure, etc.), fault cause (fuse blown, heating tube damaged, etc.), fault phenomenon (no heating, slow heating, etc.), and solution (replace fuse, repair heating tube, etc.). Relationship extraction: Determine the relationship between entities, such as "power failure" may cause "no heating" phenomenon, "replace fuse" is an effective solution to "fuse blown", etc. Attribute extraction: Extract relevant attributes for each entity, such as the classification code of the fault type, a detailed description of the fault cause, and the implementation steps of the solution.

[0112] Deduplication and merging: Deduplication of extracted knowledge is performed, and the same or similar entities, relationships and attributes are merged. Conflict resolution: For conflicting knowledge, such as different troubleshooting solutions, the final correct information is determined through expert review or data comparison. Knowledge association: Dispersed knowledge points are linked through relationships to form a network knowledge structure.

[0113] Knowledge verification: Verify the integrated knowledge to ensure the accuracy and completeness of the information. Knowledge storage: Store the verified knowledge in the form of "entity-relationship-entity" or "entity-attribute-value" in the graph database to form a knowledge graph. Model layer construction: Build a model layer on top of the data layer to extract the core concepts and rules of knowledge and manage them through the ontology library.

[0114] Troubleshooting and diagnosis: Use the fault information and solutions provided by the knowledge graph to assist users or maintenance personnel to quickly locate and solve the faults of the electric heating pot. Continuous optimization: Continuously update and improve the knowledge graph based on new fault cases and technological developments to maintain its timeliness and accuracy. Knowledge sharing: Share the knowledge graph with more users and maintenance personnel through the platform or interface to improve the efficiency of troubleshooting and maintenance.

[0115] See also Figure 2 ,The present invention provides an intelligent control system for a waterproof electric heating pot, comprising, a humidity analysis unit, which constructs a humidity value Sot at each collection point from the recorded humidity data in the working area, performs clustering processing on a number of collection points, selects a target area in the working area for the electric heating pot to operate, and records the humidity data at the collection points in the target area;

[0116] The heating prediction unit tests the electric heating pot under different simulated humid conditions, obtains the operation data of the electric heating pot, and predicts the heating time when the electric heating pot completes the heating task. If the prediction result does not meet the expectation, an adjustment instruction is issued to the outside.

[0117] The strategy dynamic control unit tests the control strategy of the electric heating pot after the control strategy library outputs the control strategy. If the control strategy is not effective enough, the parameters of the control strategy are optimized to obtain the optimized control strategy.

[0118] The error alarm unit constructs the error degree Wts from the error data difference when the electric heating pot performs the heating task, and constructs the alarm density Moj according to the time node when the error degree Qts exceeds the expected time node. If the alarm density Moj exceeds the warning threshold, a maintenance instruction is issued to the outside;

[0119] The fault maintenance unit constrains the maintenance frequency in the current stage according to the alarm density. At the maintenance node that meets the constraints, the fault maintenance knowledge graph is used to provide a maintenance plan for the electric heating pot, and the maintenance plan is executed to maintain the electric heating pot.

[0120] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0121] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0122] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0123] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only some logical function divisions. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0124] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0125] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0126] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks or optical disks.

[0127] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. An intelligent control method for a waterproof electric heating pot, characterized in that: include, The humidity value Sot at each collection point is constructed from the recorded humidity data in the working area. After clustering several collection points, a target area for the power supply heating pot to operate is selected in the working area, and the humidity data at the collection points in the target area are recorded; Conduct usage tests on the electric heating pot under different simulated humid conditions, obtain the operation data of the electric heating pot, and predict the heating time when the electric heating pot completes the heating task. If the prediction result does not meet expectations, issue adjustment instructions to the outside; After the control strategy library outputs the control strategy of the electric heating pot, the control strategy is tested. If the control strategy is not effective enough, various parameters of the control strategy are optimized to obtain the optimized control strategy. The error degree Qts is constructed by the error data difference when the electric heating pot performs the heating task, and the alarm density Moj is constructed according to the time node when the error degree Qts exceeds the expected value. If the alarm density Moj exceeds the warning threshold, a maintenance instruction is issued to the outside. The maintenance frequency in the current stage is constrained according to the alarm density. At the maintenance node that meets the constraints, the operation fault maintenance knowledge graph provides a maintenance plan for the electric heating pot, and the maintenance plan is executed to maintain the electric heating pot.

2. The intelligent control method for a waterproof electric heating pot according to claim 1, characterized in that: Construct an electronic map covering the work area and mark each collection point on the electronic map; After periodically monitoring and collecting air humidity data at each collection point, a humidity data set is generated and summarized; the humidity value Sot at the collection point is constructed from the humidity data set.

3. The intelligent control method for a waterproof electric heating pot according to claim 2, characterized in that: The collected points are marked with the obtained humidity values, and a pre-trained clustering algorithm is used to cluster several collected points, and the working area is divided into several sub-areas; Calculate the average value of humidity Sot at several collection points in the sub-area, and take the sub-area with the lowest average humidity Sot as the target area.

4. The intelligent control method for a waterproof electric heating pot according to claim 3, characterized in that: Based on the humidity data in the target area, a humid condition simulation is performed in a laboratory environment, and the electric heating pot is tested under different simulated humid conditions to obtain the operation data of the electric heating pot, which is then aggregated to generate a test operation data set; When operating the electric heating pot under humid conditions, record the heating status data, the operation data of the heating element and the humidity data in the target area.

5. The intelligent control method for a waterproof electric heating pot according to claim 4, characterized in that: Taking the heating status data and environmental condition data of the electric heating pot as input, the trained heating prediction model predicts the estimated heating time when the electric heating pot completes the heating task. If the estimated heating time is inconsistent with the target heating time, an adjustment instruction is issued to the outside.

6. The intelligent control method for a waterproof electric heating pot according to claim 5, characterized in that: After receiving the adjustment instruction, several pre-built control strategies are aggregated to build a control strategy library for the heating element; The heating state data of the electric heating pot and the operation data of the heating element are used as input, and the control strategy library outputs the corresponding control strategy for the heating element.

7. The intelligent control method for a waterproof electric heating pot according to claim 6, characterized in that: The control strategy of the electric heating pot is tested by the trained heating prediction model to obtain the estimated heating time when the heating task is completed. If the estimated heating time is still inconsistent with the target heating time, an optimization instruction is issued to the outside. The optimized control strategy is executed to control the electric heating pot, and the operation data of the electric heating pot is collected and summarized to construct the operation data set of the electric heating pot.

8. The intelligent control method for a waterproof electric heating pot according to claim 7, characterized in that: Record the time difference between the preset heating time and the expected time each time the heating task is executed, and construct the error degree Qts based on the obtained time difference Ct. If the error degree Qts exceeds the error threshold, send an alarm command to the outside; After receiving several alarm instructions in succession, the time node of the alarm instruction received in the most recent use phase is recorded and used as the alarm node. The alarm density Moj is constructed based on the alarm node. If the alarm density Moj exceeds the warning threshold, a maintenance instruction is issued to the outside.

9. The intelligent control method for a waterproof electric heating pot according to claim 8, characterized in that: After receiving the maintenance instruction, a maintenance cycle including several maintenance nodes is pre-set, and the maintenance frequency in the current stage is constrained according to the alarm density, and the electric heating pot is maintained at the maintenance nodes that meet the constraint conditions; Collect the operation data of the electric heating pot, extract features from the acquired operation data and obtain corresponding maintenance features; Taking electric heating pot fault maintenance as the target word, a knowledge graph of electric heating pot operation fault maintenance is pre-constructed.

10. An intelligent control system for a waterproof electric heating pot, characterized in that: include, The humidity analysis unit constructs the humidity value Sot at each collection point from the recorded humidity data in the working area, performs clustering on several collection points, selects a target area in the working area where the power heating pot is operated, and records the humidity data at the collection points in the target area; The heating prediction unit tests the electric heating pot under different simulated humid conditions, obtains the operation data of the electric heating pot, and predicts the heating time when the electric heating pot completes the heating task. If the prediction result does not meet the expectation, an adjustment instruction is issued to the outside. The strategy dynamic control unit tests the control strategy of the electric heating pot after the control strategy library outputs the control strategy. If the control strategy is not effective enough, the parameters of the control strategy are optimized to obtain the optimized control strategy. The error alarm unit constructs the error degree Qts from the error data difference when the electric heating pot performs the heating task, and constructs the alarm density Moj according to the time node when the error degree Qts exceeds the expected time node. If the alarm density Moj exceeds the warning threshold, a maintenance instruction is issued to the outside; The fault maintenance unit constrains the maintenance frequency in the current stage according to the alarm density. At the maintenance node that meets the constraints, the fault maintenance knowledge graph is used to provide a maintenance plan for the electric heating pot, and the maintenance plan is executed to maintain the electric heating pot.

Images