A safety test method for a hot compress salt physiotherapy pack
By detecting the humidity and agglomeration rate of particulate salts and analyzing temperature changes in machine learning models, the problems of uneven heating and unstable temperature control of the hot-compressed salt physiotherapy package are solved, achieving higher precision temperature control and safety monitoring.
Patent Information
- Application Number
- CN202411873883.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-19
- Publication Date
- 2025-07-25
- Estimated Expiration
- 2044-12-19
AI Technical Summary
The existing hot salt physiotherapy packages have reduced heat conduction efficiency due to temperature fluctuations and humidity changes during long-term use, which affects heating uniformity and temperature control accuracy, especially the temperature control of edge particle salts is unstable.
By detecting the humidity distribution and agglomeration rate of particulate salt, combining machine learning models to analyze the temperature change characteristics of the temperature sensor, establish a prediction model, and monitor the status of particulate salt in real time to prevent uneven heating and instability in temperature control.
The temperature control accuracy and heating uniformity of the hot salt physiotherapy package are improved, and abnormal state of the particle salt is discovered and prevented in a timely manner to ensure safe use.
Smart Images
Figure CN119779389B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of safety testing, and particularly relates to a method for safety testing of a hot compress salt physiotherapy pack. Background Art
[0002] The hot compress salt physiotherapy pack heats the salt pack to a suitable temperature through electric heating, and performs hot compress on the human body to promote local blood circulation and tissue metabolism, which helps to dissipate edema, inhibit inflammation, and relieve pain caused by muscle tension. In order to ensure the safety during the use of the hot compress salt physiotherapy pack, it is particularly necessary to ensure the stability of the electric heating components and temperature control of the hot compress salt physiotherapy pack.
[0003] However, for a hot compress salt physiotherapy pack using granular salt, during long-term heating and use, the humidity inside the hot compress salt physiotherapy pack may increase due to reasons such as temperature fluctuations and high air humidity, and even cause the granular salt to cake, thereby affecting the heat conduction efficiency of the granular salt, and thus affecting the heating uniformity of the hot compress salt physiotherapy pack and the accuracy of temperature control. For example, generally, at least one temperature sensor is provided at the center position of the heating part of the physiotherapy pack to monitor the temperature of the granular salt, so that the temperature control circuit controls the temperature of the physiotherapy pack. However, the humidity of the granular salt at the edge of the physiotherapy pack is too high, resulting in a decrease in heat conduction efficiency, and heat will be consumed due to the evaporation of moisture, causing the temperature rise rate of the granular salt at the edge to be lower than that of the granular salt in the central part. Since the temperature sensor monitors the temperature of the granular salt in the central part, the temperature control accuracy is reduced. Thus, when the temperature sensor monitors that the temperature of the granular salt in the central part reaches the set temperature and stops heating, the temperature of the granular salt at the edge may not have reached the set temperature yet, and even the temperature drop rate of the granular salt at the edge may increase due to the evaporation of moisture, thereby affecting the hot compress effect of the physiotherapy pack. Summary of the Invention
[0004] The purpose of the present invention is to provide a method for safety testing of a hot compress salt physiotherapy pack to solve the above deficiencies in the prior art.
[0005] To achieve the above purpose, the present invention provides the following technical solution: A method for safety testing of a hot compress salt physiotherapy pack, comprising the following steps:
[0006] S1. Prepare multiple physiotherapy packs containing granular salt in different states, detect the state of the granular salt in each physiotherapy pack to obtain the physiotherapy pack state, where the physiotherapy pack state includes the humidity distribution of the granular salt in the physiotherapy pack and the caking rate of the granular salt; wherein the internal space of the physiotherapy pack can be divided into multiple layers from the inside out, and the humidity of the granular salt in each layer is detected respectively to obtain the humidity distribution of the granular salt in the physiotherapy pack; the caking rate of the granular salt can be obtained by calculating the percentage of the volume of the caked granular salt in the total volume of the granular salt;
[0007] S2. Set the physical therapy pack status label and associate the physical therapy pack status label with the physical therapy pack corresponding to the physical therapy pack status. Among them, the physical therapy pack status label can be set according to whether the humidity of each layer exceeds the set humidity threshold. For example, the physical therapy pack is divided into an inner layer and an outer layer. The inner layer is the first layer and the outer layer is the second layer. If the humidity of the outer layer of the physical therapy pack exceeds the set humidity threshold and the humidity of the inner layer does not exceed, an outer layer abnormality label can be set and associated with the physical therapy pack;
[0008] S3. Let each physical therapy pack start heating, and at the same time, obtain the internal temperature of the physical therapy pack through the temperature sensor built in the physical therapy pack until the physical therapy pack automatically stops heating, and obtain the first temperature data. Generally, at least one temperature sensor is set at the center position of the heating part of the physical therapy pack to monitor the temperature of the granular salt, so that the temperature control circuit can stop heating when the granular salt is heated to the set first temperature threshold, such as 50 degrees Celsius, and automatically heat when the temperature of the granular salt is lower than the set second temperature threshold, such as 45 degrees Celsius. Obtaining the first temperature data can obtain the temperature change rate of the granular salt near the temperature sensor at each moment during the process of heating to the first temperature threshold, so as to judge the heat conduction efficiency of the granular salt and the overall granular salt with a negative temperature sensor through the temperature change rate, and judge whether the state of the granular salt is abnormal through the heat conduction efficiency of the granular salt, such as whether the humidity is too high or caking occurs.
[0009] S4. Associate the first temperature data with the physical therapy pack status label of the corresponding physical therapy pack, and train the first machine learning model based on the first temperature data and its associated physical therapy pack status label to obtain a first anomaly prediction model for outputting a predicted first physical therapy pack status label according to the input first temperature data; thus, it is possible to judge whether the physical therapy pack status is abnormal according to the temperature change characteristics of the granular salt near the temperature sensor of the physical therapy pack during heating.
[0010] S5. Obtain the temperature change data of the temperature sensor built in the physical therapy pack during the period from when the physical therapy pack automatically stops heating to when it automatically heats again to obtain the second temperature data;
[0011] S6. Associate the second temperature data with the physical therapy pack status label of the corresponding physical therapy pack, and train the second machine learning model based on the second temperature data and its associated physical therapy pack status label to obtain a second anomaly prediction model for outputting a predicted second physical therapy pack status label according to the input second temperature data; thus, it is possible to judge whether the physical therapy pack status is abnormal according to the temperature change characteristics of the granular salt near the temperature sensor of the physical therapy pack during cooling. Combining the temperature change characteristics during heating for judgment can further improve the judgment accuracy.
[0012] S7. Select a physical therapy pack to be tested, obtain the first temperature data of the temperature sensor built in the physical therapy pack to be tested, and input the first temperature data into the first anomaly prediction model to obtain the first physical therapy pack status label;
[0013] S8. Obtain the second temperature data of the built-in temperature sensor of the physiotherapy package to be measured, and input the second temperature data into the second anomaly prediction model to obtain the second physiotherapy package status label.
[0014] Further, the method further includes dividing the first temperature data and the second temperature data into multiple parts respectively, including the following steps:
[0015] Obtain the ambient temperature when the physiotherapy package is heated;
[0016] Set multiple ambient temperature intervals, and divide the first temperature data and the second temperature data into multiple first temperature data subsets and second temperature data subsets respectively according to the ambient temperature when the corresponding physiotherapy package works.
[0017] Further, S4 further includes the following steps:
[0018] Preprocess each first temperature data subset, where the specific steps of the preprocessing can be adjusted according to the selected first machine learning model. For example, if the first machine learning model is a long short-term memory network, the preprocessing can be data cleaning, normalization or standardization, serialization, etc.; The present invention does not limit the specific machine learning model, and specific models can be selected according to the actual situation, such as a random forest model, a neural network model, a gradient boosting tree model, etc.;
[0019] Train the first machine learning model based on each first temperature data subset respectively to obtain the corresponding first anomaly prediction sub-model, and the first anomaly prediction sub-model is used to output the probability of each physiotherapy package status label based on the input first temperature data;
[0020] Set a first output probability threshold, and make the probability of the physiotherapy package status label finally output by the first anomaly prediction sub-model greater than the first output probability threshold;
[0021] Integrate the first anomaly prediction sub-models to obtain the first anomaly prediction model, which is used to input the first temperature data into the corresponding first anomaly prediction sub-model based on the ambient temperature when the physiotherapy package corresponding to the input first temperature data is heated.
[0022] Further, S6 further includes the following steps:
[0023] Preprocess each second temperature data subset, where the specific steps of the preprocessing can be adjusted according to the selected second machine learning model;
[0024] Train the second machine learning model based on each second temperature data subset respectively to obtain the corresponding second anomaly prediction sub-model, and the second anomaly prediction sub-model is used to output the probability of each physiotherapy package status label based on the input second temperature data;
[0025] Set a second output probability threshold, and make the probability that the second abnormal prediction sub-model finally outputs the physical therapy package status label greater than the physical therapy package status label of the second output probability threshold;
[0026] Integrate the second abnormal prediction sub-model to obtain a second abnormal prediction model, which is used to input the second temperature data into the corresponding second abnormal prediction sub-model based on the ambient temperature when the physical therapy package corresponding to the input second temperature data is heated.
[0027] Further, the method further includes the following steps:
[0028] Obtain the first physical therapy package status label output by the first abnormal prediction model and the second physical therapy package status label output by the second abnormal prediction model;
[0029] Select the physical therapy package status outputs that are included in both the first physical therapy package status label and the second physical therapy package status label.
[0030] Further, the method further includes the following steps:
[0031] Classify the physical therapy package status labels, and the classification includes a normal status label and an abnormal status label;
[0032] Judge whether the output physical therapy package status label is an abnormal status label, and the physical therapy package status label includes the first physical therapy package status label and the second physical therapy package status label;
[0033] If so, give an abnormal reminder.
[0034] Further, the method further includes the following steps:
[0035] S9. Set the initial n = 1, let n = n + 1, judge whether n is greater than the set number of times, if not, return to S7.
[0036] Further, the S9 further includes the following steps:
[0037] Obtain all the first physical therapy package status labels and the second physical therapy package status labels, and respectively arrange the first physical therapy package status labels and the second physical therapy package status labels in the order of output time;
[0038] Based on the arrangement order of the first physical therapy package status label and the second physical therapy package status label, judge whether the physical therapy package status approaches the physical therapy package status corresponding to the normal status label, or whether it reaches the physical therapy package status corresponding to the normal status label;
[0039] If not, give an abnormal reminder.
[0040] Compared with the prior art, a safety test method for a hot compress salt physiotherapy pack provided by the present invention obtains historical temperature change data of an in-built temperature sensor during the working process of the physiotherapy pack and the corresponding states of the granular salt in the physiotherapy pack. According to the principle that the heat conduction efficiency of the granular salt is different in different states and the temperature change rate is different, a prediction model is established to predict the state of the granular salt in the physiotherapy pack based on the obtained temperature change data, timely detect abnormalities in the state of the granular salt, and prevent problems such as uneven heating, unstable temperature control, and low precision of the physiotherapy pack.
[0041] Compared with the prior art, a safety test method for a hot compress salt physiotherapy pack provided by the present invention further improves the accuracy of model prediction and judgment by respectively analyzing the temperature change characteristics of the granular salt in the physiotherapy pack during heating and cooling and combining them for judgment.
[0042] Compared with the prior art, a safety test method for a hot compress salt physiotherapy pack provided by the present invention repeatedly predicts the heating and cooling processes of the physiotherapy pack to determine whether the state of the granular salt in the physiotherapy pack is normal or tending to be normal, and can determine whether the physiotherapy pack requires manual intervention and maintenance. BRIEF DESCRIPTION OF THE DRAWINGS
[0043] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments recorded in the present invention, and those of ordinary skill in the art can also obtain other drawings based on these drawings.
[0044] Figure 1 It is a schematic diagram of the overall steps of the method provided by the embodiment of the present invention;
[0045] Figure 2 It is a schematic diagram of the abnormal reminder steps provided by the embodiment of the present invention;
[0046] Figure 3 It is another schematic diagram of the abnormal reminder steps provided by the embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS
[0047] In order to enable those skilled in the art to better understand the technical solutions of the present invention, the following will further introduce the present invention in detail with reference to the drawings.
[0048] In the description of the present invention, it should be understood that the terms "first" and "second" are only used for descriptive purposes and cannot be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of the said features. In the description of the present invention, "a plurality of" means two or more unless otherwise specifically defined. In addition, the terms "installed", "connected", and "connected" should be understood in a broad sense. For example, it may be a fixed connection, a detachable connection, or an integral connection; it may be a mechanical connection or an electrical connection; it may be directly connected or indirectly connected through an intermediate medium, and it may be the communication inside two components. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.
[0049] Exemplary embodiments will be described in more detail hereinafter with reference to the accompanying drawings, but the exemplary embodiments may be embodied in different forms and should not be construed as limited to the embodiments set forth herein. On the contrary, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
[0050] In the case of no conflict, the various embodiments of the present disclosure and the features in the embodiments may be combined with each other.
[0051] As used herein, the term "and / or" includes any and all combinations of one or more of the associated listed items.
[0052] The terms used herein are only for describing specific embodiments and are not intended to limit the present disclosure. As used herein, the singular forms "a" and "the" are also intended to include the plural forms unless the context clearly indicates otherwise. It will also be understood that when the terms "comprising" and / or "consisting of" are used in this specification, the specified features, wholes, steps, operations, elements, and / or components are present, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their groups.
[0053] Please refer to Figures 1 - 3 , a safety test method for a hot compress salt physiotherapy pack, comprising the following steps:
[0054] S1. Prepare a plurality of physiotherapy packs containing granular salts in different states, detect the states of the granular salts in each physiotherapy pack to obtain the physiotherapy pack state, and the physiotherapy pack state includes the humidity distribution of the granular salts in the physiotherapy pack and the caking rate of the granular salts; wherein the internal space of the physiotherapy pack can be divided into multiple layers from the inside out, and the humidity of the granular salts in each layer is detected respectively to obtain the humidity distribution of the granular salts in the physiotherapy pack; the caking rate of the granular salts can be obtained by calculating the percentage of the volume of the caked granular salts in the total volume of the granular salts;
[0055] S2. Set the physical therapy pack status label and associate the physical therapy pack status label with the physical therapy pack corresponding to the physical therapy pack status. Among them, the physical therapy pack status label can be set according to whether the humidity of each layer exceeds the set humidity threshold. For example, the physical therapy pack is divided into an inner layer and an outer layer. The inner layer is the first layer and the outer layer is the second layer. If the humidity of the outer layer of the physical therapy pack exceeds the set humidity threshold and the humidity of the inner layer does not exceed, an outer layer abnormality label can be set and associated with the physical therapy pack;
[0056] S3. Let each physical therapy pack start heating, and at the same time, obtain the internal temperature of the physical therapy pack through the temperature sensor built in the physical therapy pack until the physical therapy pack automatically stops heating, and obtain the first temperature data. Generally, at least one temperature sensor is set at the center position of the heating part of the physical therapy pack to monitor the temperature of the granular salt, so that the temperature control circuit can stop heating when the granular salt is heated to the set first temperature threshold, such as 50 °C, and automatically heat when the temperature of the granular salt is lower than the set second temperature threshold, such as 45 °C. Obtaining the first temperature data can obtain the temperature change rate at each moment during the process of heating the granular salt near the temperature sensor to the first temperature threshold, so as to judge the negative temperature sensor of the granular salt and the overall heat conduction efficiency of the granular salt through the temperature change rate, and judge whether the state of the granular salt is abnormal through the heat conduction efficiency of the granular salt, such as whether the humidity is too high or caking occurs.
[0057] S4. Associate the first temperature data with the physical therapy pack status label of the corresponding physical therapy pack, and train the first machine learning model based on the first temperature data and its associated physical therapy pack status label to obtain a first anomaly prediction model for outputting a predicted first physical therapy pack status label according to the input first temperature data; thus, it is possible to judge whether the status of the physical therapy pack is abnormal according to the temperature change characteristics during the heating of the granular salt near the temperature sensor of the physical therapy pack.
[0058] S5. Obtain the temperature change data of the temperature sensor built in the physical therapy pack during the period from the automatic stop of heating to the automatic heating again of the physical therapy pack, and obtain the second temperature data;
[0059] S6. Associate the second temperature data with the physical therapy pack status label of the corresponding physical therapy pack, and train the second machine learning model based on the second temperature data and its associated physical therapy pack status label to obtain a second anomaly prediction model for outputting a predicted second physical therapy pack status label according to the input second temperature data; thus, it is possible to judge whether the status of the physical therapy pack is abnormal according to the temperature change characteristics during the cooling of the granular salt near the temperature sensor of the physical therapy pack. Combining the temperature change characteristics during heating for judgment can further improve the accuracy of judgment.
[0060] S7. Select the physical therapy pack to be tested, obtain the first temperature data of the temperature sensor built in the physical therapy pack to be tested, and input the first temperature data into the first anomaly prediction model to obtain the first physical therapy pack status label;
[0061] S8. Obtain the second temperature data of the built-in temperature sensor of the physiotherapy pack to be measured, input the second temperature data into the second anomaly prediction model, and obtain the second physiotherapy pack status label. Further, obtain the first physiotherapy pack status label output by the first anomaly prediction model and the second physiotherapy pack status label output by the second anomaly prediction model; select and output the physiotherapy pack statuses included in both the first physiotherapy pack status label and the second physiotherapy pack status label.
[0062] S9. Set the initial n = 1, let n = n + 1, and determine whether n is greater than the set number of times. If not, return to S7.
[0063] Further, S9 also includes the following steps:
[0064] Obtain all the first physiotherapy pack status labels and the second physiotherapy pack status labels, and sort the first physiotherapy pack status labels and the second physiotherapy pack status labels in the order of output time;
[0065] Based on the sorting order of the first physiotherapy pack status label and the second physiotherapy pack status label, determine whether the physiotherapy pack status approaches the physiotherapy pack status corresponding to the normal status label or reaches the physiotherapy pack status corresponding to the normal status label;
[0066] If not, give an anomaly reminder.
[0067] In one embodiment, the method further includes dividing the first temperature data and the second temperature data into multiple parts respectively, including the following steps:
[0068] Obtain the ambient temperature when the physiotherapy pack is heated;
[0069] Set multiple ambient temperature intervals, and divide the first temperature data and the second temperature data into multiple first temperature data subsets and second temperature data subsets respectively according to the ambient temperature when the corresponding physiotherapy pack works.
[0070] S4 also includes the following steps:
[0071] Preprocess each first temperature data subset, where the specific steps of the preprocessing can be adjusted according to the selected first machine learning model. For example, if the first machine learning model is a long short-term memory network, the preprocessing can be data cleaning, normalization or standardization, serialization, etc.; the present invention does not limit the specific machine learning model, and a specific model can be selected according to the actual situation, such as a random forest model, a neural network model, a gradient boosting tree model, etc.;
[0072] Train the first machine learning model based on each first temperature data subset respectively to obtain the corresponding first anomaly prediction sub-model, and the first anomaly prediction sub-model is used to output the probability of each physiotherapy pack status label based on the input first temperature data.
[0073] Set a first output probability threshold, and the physical therapy package status label whose probability of the first anomaly prediction sub-model finally outputting the physical therapy package status label is greater than the first output probability threshold;
[0074] Integrate the first anomaly prediction sub-model to obtain a first anomaly prediction model, which is used to input the first temperature data into the corresponding first anomaly prediction sub-model based on the ambient temperature when the physical therapy package corresponding to the input first temperature data is heated.
[0075] S6 also includes the following steps:
[0076] Preprocess each second temperature data subset, and the specific steps of the preprocessing can be adjusted according to the selected second machine learning model;
[0077] Train a second machine learning model based on each second temperature data subset respectively to obtain a corresponding second anomaly prediction sub-model, and the second anomaly prediction sub-model is used to output the probability of each physical therapy package status label based on the input second temperature data;
[0078] Set a second output probability threshold, and the physical therapy package status label whose probability of the second anomaly prediction sub-model finally outputting the physical therapy package status label is greater than the second output probability threshold;
[0079] Integrate the second anomaly prediction sub-model to obtain a second anomaly prediction model, which is used to input the second temperature data into the corresponding second anomaly prediction sub-model based on the ambient temperature when the physical therapy package corresponding to the input second temperature data is heated.
[0080] In one embodiment, the method further includes the following steps:
[0081] Classify the physical therapy package status labels, and the classification includes a normal status label and an abnormal status label;
[0082] Judge whether the output physical therapy package status label is an abnormal status label, and the physical therapy package status label includes a first physical therapy package status label and a second physical therapy package status label;
[0083] If so, give an abnormal reminder.
[0084] Only some exemplary embodiments of the present invention are described by way of illustration above. Undoubtedly, for those of ordinary skill in the art, without departing from the spirit and scope of the present invention, the described embodiments can be modified in various different ways. Therefore, the above drawings and descriptions are illustrative in nature and should not be construed as limiting the protection scope of the claims of the present invention.
Claims
1. A safety test method for a hot compress salt physiotherapy pack, characterized in that: It includes the following steps: S1. Prepare multiple physiotherapy packs containing granular salt in different states, detect the state of the granular salt in each physiotherapy pack, and obtain the state of the physiotherapy pack; S2. Set the physiotherapy pack state label and associate the physiotherapy pack state label with the corresponding physiotherapy pack; S3. Start heating each physiotherapy pack, and at the same time, obtain the internal temperature of the physiotherapy pack through the built-in temperature sensor of the physiotherapy pack until the physiotherapy pack automatically stops heating, and obtain the first temperature data; S4. Associate the first temperature data with the physiotherapy pack state label of the corresponding physiotherapy pack, and train the first machine learning model based on the first temperature data and its associated physiotherapy pack state label to obtain the first anomaly prediction model for outputting the predicted first physiotherapy pack state label according to the input first temperature data; S5. Obtain the temperature change data of the built-in temperature sensor of the physiotherapy pack during the period from automatically stopping heating to automatically heating again, and obtain the second temperature data; S6. Associate the second temperature data with the physiotherapy pack state label of the corresponding physiotherapy pack, and train the second machine learning model based on the second temperature data and its associated physiotherapy pack state label to obtain the second anomaly prediction model for outputting the predicted second physiotherapy pack state label according to the input second temperature data; S7. Select a physiotherapy pack to be tested, obtain the first temperature data of the built-in temperature sensor of the physiotherapy pack to be tested, and input the first temperature data into the first anomaly prediction model to obtain the first physiotherapy pack state label; S8. Obtain the second temperature data of the built-in temperature sensor of the physiotherapy pack to be tested, and input the second temperature data into the second anomaly prediction model to obtain the second physiotherapy pack state label.
2. The safety test method for a hot compress salt physiotherapy pack according to claim 1, wherein: The method further includes dividing the first temperature data and the second temperature data into multiple parts respectively, and includes the following steps: Obtain the ambient temperature when the physiotherapy pack is heated; Set multiple ambient temperature intervals, and divide the first temperature data and the second temperature data into multiple first temperature data subsets and second temperature data subsets respectively according to the ambient temperature when the corresponding physiotherapy pack works.
3. A safety test method for a hot compress salt physiotherapy pack according to claim 2, characterized in that: The S4 further includes the following steps: Train the first machine learning model based on each first temperature data subset respectively to obtain the corresponding first anomaly prediction sub-model, and the first anomaly prediction sub-model is used to output the probability of each physiotherapy pack state label based on the input first temperature data; Set the first output probability threshold to make the probability of the physiotherapy pack state label finally output by the first anomaly prediction sub-model greater than the first output probability threshold; Integrate the first anomaly prediction sub-models to obtain the first anomaly prediction model, which is used to input the first temperature data into the corresponding first anomaly prediction sub-model based on the ambient temperature when the physiotherapy pack corresponding to the input first temperature data is heated.
4. A safety test method for a hot compress salt physiotherapy pack according to claim 2, characterized in that: The S6 further includes the following steps: Train the second machine learning model based on each second temperature data subset respectively to obtain the corresponding second anomaly prediction sub-model, and the second anomaly prediction sub-model is used to output the probability of each physiotherapy pack state label based on the input second temperature data; Set a second output probability threshold, and the physical therapy package status label for which the probability that the second anomaly prediction sub-model finally outputs the physical therapy package status label is greater than the second output probability threshold; Integrate the second anomaly prediction sub-model to obtain a second anomaly prediction model, which is used to input the second temperature data into the corresponding second anomaly prediction sub-model based on the ambient temperature when the physical therapy package corresponding to the input second temperature data is heated.
5. A safety test method for a hot compress salt physiotherapy pack according to claim 1, characterized in that: The method further includes the following steps: Obtain the first physical therapy package status label output by the first anomaly prediction model and the second physical therapy package status label output by the second anomaly prediction model; Select the physical therapy package status output that is included in both the first physical therapy package status label and the second physical therapy package status label.
6. The safety test method for a hot compress salt physiotherapy pack according to claim 1, wherein: The method further includes the following steps: Classify the physical therapy package status label, and the classification includes a normal status label and an abnormal status label; Judge whether the output physical therapy package status label is an abnormal status label, and the physical therapy package status label includes the first physical therapy package status label and the second physical therapy package status label; If so, give an anomaly reminder.
7. A safety test method for a hot compress salt physiotherapy pack according to claim 6, characterized in that: The method further includes the following steps: S9. Set the initial n = 1, let n = n + 1, judge whether n is greater than the set number of times, if not, return to S7.
8. A safety test method for a hot compress salt physiotherapy pack according to claim 7, characterized in that: The S9 further includes the following steps: Obtain all the first physical therapy package status labels and the second physical therapy package status labels, and arrange the first physical therapy package status label and the second physical therapy package status label in the order of output time; Based on the arrangement order of the first physical therapy package status label and the second physical therapy package status label, judge whether the physical therapy package status approaches the physical therapy package status corresponding to the normal status label, or whether it reaches the physical therapy package status corresponding to the normal status label; If not, give an anomaly reminder.
Citation Information
Patent Citations
Device and method for testing heat-conducting property of molten salt nanoparticle suspension
CN114740042A
Power station peak regulation system and method based on high-capacity high-temperature fused salt energy storage
CN116718059A