Intelligent HAST equipment adjusting method and system based on multi-source heterogeneous data and medium

Abstract

The invention provides an intelligent HAST equipment adjusting method and system based on multi-source heterogeneous data and a medium, the heterogeneous data is collected in real time based on temperature, humidity and pressure sensors, the instantaneous change rate and the sliding window mean value are calculated through a difference algorithm, the optimal cooling mode is matched in combination with a preset rule base, and the optimal cooling mode is obtained. The problems of control lag and misoperation caused by the fact that traditional equipment depends on a single threshold value are solved; in the initialization stage, a modeling driver parameter template is loaded, dynamic adjustment is conducted according to the real-time change rate in the operation process, the fan rotating speed is optimized through a fuzzy PID algorithm, an ARIMA time sequence model is introduced to predict the future trend, the exhausting or cooling action is triggered in advance, and passive response is avoided; and when the parameter mean value exceeds a safety threshold value, executing emergency shutdown in a grading manner and recording an over-limit event to ensure the safety of equipment and samples.

Description

Technical Field

[0001] The present invention relates to the field of HAST equipment, and more specifically, to a method, system and medium for intelligently adjusting HAST equipment based on multi-source heterogeneous data. Background Art

[0002] Highly Accelerated Stress Test (HAST) equipment is widely used for reliability testing of electronic components, polymer materials, and packaged devices. It simulates accelerated product aging through high-temperature, high-humidity, and high-pressure environments to assess their lifespan and failure modes. In the control logic of traditional HAST equipment, relay action relies on fixed thresholds and lacks the ability to coordinate and respond to dynamic changes in multiple parameters, leading to delayed environmental control or malfunctions. Furthermore, the single cooling mode is unable to adapt to the temperature-sensitive characteristics of different materials.

[0003] Although existing technologies have attempted to introduce PID control or simple logical judgment, it is still difficult to achieve deep integration and dynamic decision-making of multi-source heterogeneous data, and lacks forward-looking control capabilities.

[0004] Therefore, there is an urgent need for an intelligent adjustment technology for HAST equipment based on dynamic analysis and predictive control of multi-source data. Summary of the Invention

[0005] In view of the above problems, the purpose of the present invention is to provide a method, system and medium for intelligent adjustment of HAST equipment based on multi-source heterogeneous data, which avoids system instability caused by single-factor adjustment through real-time collaborative control of multi-source heterogeneous data; adaptively selects cooling mode through calculation of sensor data change rate, taking into account both efficiency and sample protection; predicts and actively avoids abnormal risks, reduces test interruptions and equipment losses; thereby breaking through the limitations of traditional static logic and providing technical support for high-precision and high-reliability testing.

[0006] A first aspect of the present invention provides a HAST equipment intelligent adjustment method based on multi-source heterogeneous data, the method comprising:

[0007] According to a preset collection cycle, multi-source heterogeneous data is collected based on preset sensors, wherein the multi-source heterogeneous data includes temperature values, humidity values, and pressure values;

[0008] According to the multi-source heterogeneous data, a multi-source heterogeneous change rate and a multi-source heterogeneous mean are obtained;

[0009] matching a cooling mode according to the multi-source heterogeneous change rate and the multi-source heterogeneous mean;

[0010] Initializing driver parameters based on the cooling mode, wherein the driver parameters include exhaust valve opening, fan speed, heating relay switching time, and humidification relay switching time;

[0011] adjusting driver parameters according to the multi-source heterogeneous change rate;

[0012] Predicting a change trend based on the multi-source heterogeneous change rate and the multi-source heterogeneous mean, and using this to adjust driver parameters;

[0013] Store the adjustment drive operation record in the log;

[0014] If the multi-source heterogeneous mean exceeds a preset over-limit threshold, an over-limit mechanism is triggered to shut down the corresponding driver.

[0015] In this solution, the multi-source heterogeneous data is collected based on the preset sensors according to the preset collection period, specifically:

[0016] According to the preset collection cycle, the original values ​​of temperature, humidity and pressure in the box are collected synchronously through temperature sensors, humidity sensors and pressure sensors;

[0017] According to the preset amount of data, a sliding window is determined to store the original value;

[0018] According to the original value in the sliding window, a preset linear interpolation method is used to complete the window data;

[0019] According to the window data, multi-source heterogeneous data is obtained based on a preset filtering algorithm.

[0020] In this solution, the multi-source heterogeneous data is used to obtain the multi-source heterogeneous change rate and the multi-source heterogeneous mean, specifically:

[0021] Obtaining the multi-source heterogeneous instantaneous change rate based on the temperature, humidity and pressure data of the multi-source heterogeneous data and a preset differential algorithm;

[0022] According to the temperature, humidity and pressure data of the multi-source heterogeneous data, based on a preset first window duration, a linear regression algorithm is used to obtain a multi-source heterogeneous trend change rate;

[0023] According to the temperature, humidity and pressure data of the multi-source heterogeneous data, based on a preset second window duration, an arithmetic mean algorithm is used to obtain a multi-source heterogeneous mean;

[0024] According to the multi-source heterogeneous mean, based on a preset normalization process, a multi-dimensional feature vector is obtained.

[0025] In this solution, the cooling mode is matched according to the multi-source heterogeneous change rate and the multi-source heterogeneous mean, specifically:

[0026] If the average temperature exceeds the target temperature, the temperature change rate exceeds the preset first temperature change threshold, and the pressure change rate is within the preset pressure stability range, it is determined to be in rapid cooling mode;

[0027] If the temperature change rate is lower than a preset first temperature change threshold and the pressure average exceeds a preset first pressure threshold, it is determined to be a slow cooling mode;

[0028] Or, if there is a sensitive material mark, it is determined to be a slow cooling mode;

[0029] If the average humidity is lower than the preset humidity target, the humidity change rate is lower than the preset first humidity change threshold, and the temperature change rate is negative, it is determined to be in moisturizing cooling mode;

[0030] Select a cooling mode based on the preset priority strategy.

[0031] This plan also includes:

[0032] When it is judged to be the rapid cooling mode, the exhaust valve opening is 100%, the fan speed is 100%, the heating relay is closed, and the humidification relay is closed;

[0033] When the slow cooling mode is determined, the exhaust valve opening is 50%, the fan speed is 80%, and the heating relay maintains the minimum closing time. The exhaust valve opening and fan speed are gradually reduced according to the preset steps.

[0034] When it is determined to be the moisturizing cooling mode, the exhaust valve is set to open 10% according to the preset moisturizing cycle, the fan is turned off, and the humidification relay is turned on.

[0035] In this solution, the driver parameters are adjusted according to the multi-source heterogeneous change rate, specifically:

[0036] If the humidity change rate is higher than a preset second humidity change threshold, the closing time of the humidification relay is linearly shortened;

[0037] If the pressure change rate is higher than a preset first pressure change threshold, shortening the exhaust valve opening according to a preset step;

[0038] Based on the preset fuzzy PID algorithm, the fan speed is adjusted according to the deviation of the average temperature and average humidity from the target value.

[0039] A second aspect of the present invention provides a HAST device intelligent adjustment system based on multi-source heterogeneous data, including a HAST device intelligent adjustment method program based on multi-source heterogeneous data, wherein the HAST device intelligent adjustment method program based on multi-source heterogeneous data, when executed by the processor, implements the following steps:

[0040] According to a preset collection cycle, multi-source heterogeneous data is collected based on preset sensors, wherein the multi-source heterogeneous data includes temperature values, humidity values, and pressure values;

[0041] According to the multi-source heterogeneous data, a multi-source heterogeneous change rate and a multi-source heterogeneous mean are obtained;

[0042] matching a cooling mode according to the multi-source heterogeneous change rate and the multi-source heterogeneous mean;

[0043] Initializing driver parameters based on the cooling mode, wherein the driver parameters include exhaust valve opening, fan speed, heating relay switching time, and humidification relay switching time;

[0044] adjusting driver parameters according to the multi-source heterogeneous change rate;

[0045] Predicting a change trend based on the multi-source heterogeneous change rate and the multi-source heterogeneous mean, and using this to adjust driver parameters;

[0046] Store the adjustment drive operation record in the log;

[0047] If the multi-source heterogeneous mean exceeds a preset over-limit threshold, an over-limit mechanism is triggered to shut down the corresponding driver.

[0048] In this solution, the multi-source heterogeneous data is collected based on the preset sensors according to the preset collection period, specifically:

[0049] According to the preset collection cycle, the original values ​​of temperature, humidity and pressure in the box are collected synchronously through temperature sensors, humidity sensors and pressure sensors;

[0050] According to the preset amount of data, a sliding window is determined to store the original value;

[0051] According to the original value in the sliding window, a preset linear interpolation method is used to complete the window data;

[0052] According to the window data, multi-source heterogeneous data is obtained based on a preset filtering algorithm.

[0053] In this solution, the multi-source heterogeneous data is used to obtain the multi-source heterogeneous change rate and the multi-source heterogeneous mean, specifically:

[0054] Obtaining the multi-source heterogeneous instantaneous change rate based on the temperature, humidity and pressure data of the multi-source heterogeneous data and a preset differential algorithm;

[0055] According to the temperature, humidity and pressure data of the multi-source heterogeneous data, based on a preset first window duration, a linear regression algorithm is used to obtain a multi-source heterogeneous trend change rate;

[0056] According to the temperature, humidity and pressure data of the multi-source heterogeneous data, based on a preset second window duration, an arithmetic mean algorithm is used to obtain a multi-source heterogeneous mean;

[0057] According to the multi-source heterogeneous mean, based on a preset normalization process, a multi-dimensional feature vector is obtained.

[0058] The third aspect of the present invention provides a computer-readable storage medium, which includes a HAST device intelligent adjustment method program based on multi-source heterogeneous data. When the HAST device intelligent adjustment method program based on multi-source heterogeneous data is executed by a processor, the steps of the HAST device intelligent adjustment method based on multi-source heterogeneous data as described in any one of the above items are implemented.

[0059] The present invention provides a HAST equipment intelligent adjustment method, system and medium based on multi-source heterogeneous data. The method collects heterogeneous data in real time based on temperature, humidity and pressure sensors, calculates the instantaneous change rate and sliding window mean through a differential algorithm, and matches the optimal cooling mode in combination with a preset rule base to solve the control lag and malfunction problems caused by traditional equipment relying on a single threshold. The method loads a patterned driver parameter template in the initialization phase, and dynamically adjusts it according to the real-time change rate during operation. The fan speed is optimized through a fuzzy PID algorithm, and an ARIMA time series model is introduced to predict future trends, so as to trigger exhaust or cooling actions in advance and avoid passive response. When the parameter mean exceeds the safety threshold, an emergency shutdown is performed in stages and the over-limit event is recorded to ensure the safety of the equipment and samples. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. It should be understood that the following drawings only illustrate certain embodiments of the present invention and therefore should not be regarded as limiting the scope.

[0061] Figure 1 A flow chart of a HAST equipment intelligent adjustment method based on multi-source heterogeneous data according to the present invention is shown;

[0062] Figure 2 A flowchart for collecting multi-source heterogeneous data is shown in an embodiment of the present invention;

[0063] Figure 3 A flowchart of processing multi-source heterogeneous data is shown in an embodiment of the present invention;

[0064] Figure 4 A block diagram of an intelligent adjustment system for HAST equipment based on multi-source heterogeneous data of the present invention is shown. DETAILED DESCRIPTION

[0065] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. 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 making creative efforts are within the scope of protection of the present invention.

[0066] Unless otherwise defined, all terms (including technical and scientific terms) used in the embodiments of the present invention have the same meaning as commonly understood by those skilled in the art to which the present invention belongs. It should also be understood that terms such as those defined in common dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant technology, and should not be interpreted in an idealized or extremely formal sense, unless explicitly defined in this manner in the embodiments of the present invention.

[0067] The terms "first," "second," and similar words used in the embodiments of the present invention do not indicate any order, quantity, or importance, but are only used to distinguish different components. Terms such as "a," "an," or "the" do not indicate a limit on quantity, but rather indicate the presence of at least one. Similarly, terms such as "include," "comprise," and "comprising" mean that the elements or objects preceding the term include the elements or objects listed after the term and their equivalents, without excluding other elements or objects.

[0068] "Connected" or "connected" and similar terms are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The preceding or subsequent steps of the methods of the embodiments of the present invention do not necessarily need to be performed in exact order. Instead, various steps may be performed in reverse order or simultaneously. Furthermore, other operations may be added to these processes, or one or more steps may be removed from these processes.

[0069] In addition, the functional modules in the various embodiments of the present invention may be integrated together to form an independent part, or each module may exist independently, or two or more modules may be integrated to form an independent part.

[0070] Figure 1 The flowchart of the present invention shows a HAST equipment intelligent adjustment method based on multi-source heterogeneous data.

[0071] like Figure 1 As shown, the first aspect of the present invention discloses a HAST equipment intelligent adjustment method based on multi-source heterogeneous data, the method comprising:

[0072] S102, collecting multi-source heterogeneous data based on preset sensors according to a preset collection cycle, wherein the multi-source heterogeneous data includes temperature values, humidity values, and pressure values;

[0073] S104, obtaining a multi-source heterogeneous change rate and a multi-source heterogeneous mean based on the multi-source heterogeneous data;

[0074] S106, matching a cooling mode according to the multi-source heterogeneous change rate and the multi-source heterogeneous mean;

[0075] S108, initializing driver parameters based on the cooling mode, wherein the driver parameters include exhaust valve opening, fan speed, heating relay switching time, and humidification relay switching time;

[0076] S110, adjusting driver parameters according to the multi-source heterogeneous change rate;

[0077] S112, predicting a change trend based on the multi-source heterogeneous change rate and the multi-source heterogeneous mean, for adjusting driver parameters;

[0078] S114, storing the driver adjustment operation record in a log;

[0079] S116: If the multi-source heterogeneous mean exceeds a preset over-limit threshold, an over-limit mechanism is triggered to shut down the corresponding driver.

[0080] It should be noted that in this embodiment, the raw data of the environmental parameters within the test chamber are first collected synchronously using a PT1000 temperature sensor, a humidity probe sensor, and an SMC ISE30A pressure sensor at a preset collection cycle (e.g., once per second) to ensure real-time data. After collection is completed, the system preprocesses and combines the raw data to obtain multi-source heterogeneous data, including sliding window filtering to eliminate noise and linear interpolation to fill missing values. Secondly, based on the multi-source heterogeneous data, the instantaneous rate of change, trend rate of change, and sliding window mean of each environmental parameter are calculated to form a multidimensional feature vector. Based on a preset pattern rule library, the optimal cooling mode is matched by combining the instantaneous rate of change, trend rate of change, and sliding window mean of each environmental parameter. For example, when the temperature is high and rising rapidly, a fast cooling mode is selected. Then, during the initialization phase of each driver, the corresponding driver parameter template is set according to the selected cooling mode, and the parameters are dynamically adjusted during operation. Finally, a time series model is used to predict future trends of temperature, humidity, and pressure, and the driver action is adjusted in advance to avoid over-limit. All operation records and sensor data are stored in log files for subsequent analysis and adjustment of the prediction parameters of the time series model. In addition, when it is detected that the mean value of the environmental parameter exceeds the safety threshold, the over-limit mechanism is immediately triggered, including but not limited to shutting down the heater and fully opening the exhaust valve to ensure the safety of the equipment and samples. This embodiment first dynamically adapts to complex environmental changes through collaborative analysis of multi-source data to avoid the limitations of single parameter control. Then, through real-time adjustment and prediction functions, the control accuracy is significantly improved, the risk of equipment over-limit is reduced, and finally dynamic correction is made through log records to improve the credibility of the test data.

[0081] Figure 2 A flowchart for collecting multi-source heterogeneous data is shown in an embodiment of the present invention.

[0082] According to an embodiment of the present invention, Figure 2 As shown, the multi-source heterogeneous data is collected based on the preset sensors according to the preset collection period, specifically:

[0083] S202, according to a preset collection cycle, synchronously collect the original values ​​of temperature, humidity and pressure in the box through the temperature sensor, humidity sensor and pressure sensor;

[0084] S204, determining a sliding window based on a preset amount of data for storing the original value;

[0085] S206, using a preset linear interpolation method to complete the window data according to the original value in the sliding window;

[0086] S208 , obtaining multi-source heterogeneous data based on the window data and a preset filtering algorithm.

[0087] It should be noted that in this embodiment, during the data collection phase, the temperature, humidity, and pressure sensors are triggered synchronously via the bus to ensure that the timestamps are aligned.

[0088] Figure 3 The present invention shows a flowchart for processing multi-source heterogeneous data provided by an embodiment of the present invention. The acquisition cycle can be configured according to the test requirements to adapt to the dynamic characteristics of different test samples. The number of data in the sliding window is determined based on the data acquisition cycle. For example, the number of data with an acquisition cycle of 500ms is 10, and the number of data with an acquisition cycle of 1s is 5. The sliding window memory is set according to the number of data to store the raw data output by the sensor. If the raw data in the window memory is incorrect due to abnormalities such as sensor signal interruption, linear interpolation of the previous and next data is used to ensure data continuity. Then, high-frequency noise is eliminated by a moving average filtering algorithm, and low-pass filtering is additionally used for pressure data to suppress mechanical vibration interference. The processed data is classified by type and stored in the corresponding temperature buffer area, humidity buffer area, and pressure buffer area. This embodiment ensures data integrity through synchronous acquisition and interpolation completion, and uses filtering processing to improve data quality and reduce noise interference.

[0089] According to an embodiment of the present invention, Figure 3 As shown, the multi-source heterogeneous data is used to obtain the multi-source heterogeneous change rate and the multi-source heterogeneous mean, which are specifically:

[0090] S302, obtaining a multi-source heterogeneous instantaneous change rate based on the temperature, humidity and pressure data of the multi-source heterogeneous data using a preset difference algorithm;

[0091] S304, obtaining a multi-source heterogeneous trend change rate using a linear regression algorithm based on the temperature, humidity, and pressure data of the multi-source heterogeneous data and a preset first window duration;

[0092] S306, obtaining a multi-source heterogeneous mean value by using an arithmetic mean algorithm based on the temperature, humidity, and pressure data of the multi-source heterogeneous data and a preset second window duration;

[0093] S308 : Obtain a multi-dimensional feature vector according to the multi-source heterogeneous mean value and based on a preset normalization process.

[0094] It should be noted that this embodiment processes multi-source heterogeneous data to obtain a multi-source heterogeneous change rate and a multi-source heterogeneous mean, respectively. The multi-source heterogeneous change rate includes the multi-source heterogeneous instantaneous change rate and the multi-source heterogeneous trend change rate. First, the instantaneous change rate is calculated for the preprocessed temperature, humidity, and pressure data. For example, the difference between the current value and the previous measurement is divided by the acquisition interval to obtain the multi-source heterogeneous instantaneous change rate. Second, a linear regression analysis is performed on the multi-source heterogeneous data based on a 20-second sliding window. The slope of the regression analysis is used as the multi-source heterogeneous trend change rate. Then, the arithmetic mean is calculated based on a 10-second sliding window to obtain the multi-source heterogeneous mean. Finally, the change rate and mean of the multi-source heterogeneous data are normalized, and the parameters of different dimensions are mapped to the interval [0, 1] to obtain a multidimensional feature vector for pattern matching. This embodiment combines the instantaneous change rate with the trend change rate to comprehensively reflect the dynamic characteristics of environmental data.

[0095] According to an embodiment of the present invention, matching the cooling mode according to the multi-source heterogeneous change rate and the multi-source heterogeneous mean is specifically as follows:

[0096] If the average temperature exceeds the target temperature, the temperature change rate exceeds the preset first temperature change threshold, and the pressure change rate is within the preset pressure stability range, it is determined to be in rapid cooling mode;

[0097] If the temperature change rate is lower than a preset first temperature change threshold and the pressure average exceeds a preset first pressure threshold, it is determined to be a slow cooling mode;

[0098] Or, if there is a sensitive material mark, it is determined to be a slow cooling mode;

[0099] If the average humidity is lower than the preset humidity target, the humidity change rate is lower than the preset first humidity change threshold, and the temperature change rate is negative, it is determined to be in moisturizing cooling mode;

[0100] Select a cooling mode based on the preset priority strategy.

[0101] It should be noted that based on the preset cooling mode rule base, fast cooling mode, slow cooling mode, and moisturizing cooling mode are defined. As an implementation, when the average temperature exceeds the target value and the rate of change exceeds a first temperature change threshold (e.g., a 2°C increase per minute), while the pressure value fluctuates within a preset stability range, the fast cooling mode is determined. If the temperature change rate is below a second temperature change threshold (e.g., less than 1°C per minute), and the pressure value is below a preset first pressure threshold, the slow cooling mode is determined. If the test material is marked as sensitive, only the slow cooling mode is set. When the average humidity value is below a preset humidity target, the humidity change rate is below a preset first humidity change threshold, and the temperature is decreasing, the moisturizing cooling mode is determined. If multiple conditions are met simultaneously, conflicts are resolved according to the preset priority, where the priority is high temperature risk > high pressure risk > high humidity risk = low humidity risk. This embodiment uses multi-dimensional linkage to avoid misselection of modes, improve decision-making rationality, and prioritize high-risk scenarios based on a priority strategy, enhancing device safety.

[0102] According to an embodiment of the present invention, the further embodiment includes:

[0103] When it is judged to be the rapid cooling mode, the exhaust valve opening is 100%, the fan speed is 100%, the heating relay is closed, and the humidification relay is closed;

[0104] When the slow cooling mode is determined, the exhaust valve opening is 50%, the fan speed is 80%, and the heating relay maintains the minimum closing time. The exhaust valve opening and fan speed are gradually reduced according to the preset steps.

[0105] When it is determined to be the moisturizing cooling mode, the exhaust valve is set to open 10% according to the preset moisturizing cycle, the fan is turned off, and the humidification relay is turned on.

[0106] It should be noted that this embodiment loads a preset driver parameter template based on the cooling mode. As an implementation, in rapid cooling mode, the exhaust valve is fully open, the fan runs at full speed, and the heating and humidification functions are disabled to achieve rapid cooling. In slow cooling mode, the exhaust valve opening and fan speed are gradually reduced to maintain minimum heating power to prevent sudden temperature drops. In moist cooling mode, the exhaust valve is periodically opened, for example, for 10 seconds every minute, and the fan is disabled to maintain stable humidity.

[0107] According to an embodiment of the present invention, adjusting the driver parameters according to the multi-source heterogeneous change rate is specifically as follows:

[0108] If the humidity change rate is higher than a preset second humidity change threshold, linearly shortening the closing time of the humidification relay;

[0109] If the pressure change rate is higher than a preset first pressure change threshold, shortening the exhaust valve opening according to a preset step;

[0110] Based on the preset fuzzy PID algorithm, the fan speed is adjusted according to the deviation of the average temperature and average humidity from the target value.

[0111] It should be noted that this embodiment dynamically adjusts driver parameters based on real-time, multi-source, heterogeneous change rates. Regarding humidity control, if the monitored humidity change rate exceeds a preset second humidity change threshold, for example, a drop of more than 3% RH per minute, the humidification relay's off time is linearly shortened. In one embodiment, the initial off time is 30 seconds. Each time a humidity deviation exceeds the threshold, the off time is reduced by 5 seconds, up to a minimum off time of 10 seconds, accelerating the humidification response. This embodiment dynamically shortens the humidification interval to prevent condensation on the sample surface caused by sudden drops in humidity. Regarding pressure control, when the pressure change rate exceeds a preset first pressure change threshold, for example, an increase of 0.05 MPa per minute, a step-by-step adjustment strategy is initiated. In one embodiment, the exhaust valve opening is reduced by 5% every 10 seconds until the pressure change rate falls back within a safe range. The time and opening value of each adjustment are recorded. This embodiment uses step-by-step adjustment of the exhaust valve opening to prevent sudden pressure changes from causing damage to the device structure. In temperature control, a fuzzy PID algorithm is used to dynamically adjust fan speed. As one implementation, the input parameters include the deviation between the current temperature and the target temperature, and the deviation between the current humidity and the target humidity. The output is the fan speed adjustment. The algorithm automatically switches control PID parameters based on the magnitude of the deviation, prioritizing integral control for small deviations and proportional control for large deviations to ensure a stable cooling rate. This embodiment uses a fuzzy PID algorithm to balance response speed and stability, reducing temperature fluctuations.

[0112] It is worth mentioning that, based on the multi-source heterogeneous change rate and the multi-source heterogeneous mean, the change trend is predicted as follows:

[0113] Based on the ARIMA time series model, predict the temperature, humidity and pressure values ​​within the preset forecast period in the future;

[0114] If the predicted value exceeds a preset safety threshold, the exhaust valve opening, fan speed, heating relay switching time or humidification relay switching time are adjusted in advance;

[0115] The predicted values ​​are compared with multi-source heterogeneous data collected in real time to dynamically correct the parameters of the ARIMA time series model.

[0116] It should be noted that this embodiment uses historical data and a pre-trained ARIMA time series model to predict future parameter change trends. As an implementation, the temperature, humidity, and pressure series from the past 5 minutes are used to predict parameter changes within the next 10 seconds. During the temperature prediction process, if the model output indicates that the temperature will exceed the safety threshold within the next 5 seconds, a pre-action is triggered in advance, including gradually increasing the exhaust valve opening from the current value to 100% and increasing the fan speed to maximum power to accelerate heat dissipation. For pressure prediction, if the model predicts that the pressure will exceed 0.3 MPa, the system activates a pressure smoothing strategy, including limiting the maximum exhaust valve operation frequency to once every 5 seconds and reducing the opening adjustment amplitude to 2% each time to avoid pressure fluctuations caused by frequent opening and closing. The predicted results are compared with the actual collected data once at a set period. If the prediction error exceeds the set threshold for three consecutive times, the model parameter correction process is automatically triggered, including reselecting the sliding window size and refitting the ARIMA coefficients based on the latest data. The corrected model is immediately put into real-time prediction to ensure prediction accuracy. This embodiment adjusts the driver parameters in advance to avoid equipment over-limit caused by passive response. At the same time, based on the dynamic correction prediction model, it adapts to the environmental characteristics of different test stages.

[0117] It is worth mentioning that if the multi-source heterogeneous mean exceeds the preset over-limit threshold, the over-limit mechanism is triggered and the corresponding driver is shut down, specifically:

[0118] If the average temperature exceeds the preset temperature over-limit threshold, the heating relay is turned off, the exhaust valve opening is 100%, and the fan speed is 100%;

[0119] If the average humidity value is lower than the preset humidity over-limit range, the humidification relay is turned on and the exhaust valve is opened by 10%;

[0120] If the average humidity value is higher than the preset humidity limit range, the humidification relay is turned off, the exhaust valve opening is 100%, and the fan speed is 100%;

[0121] If the average pressure is higher than the preset pressure over-limit threshold, the heating relay is turned off, the humidification relay is turned off, and the exhaust valve opening is gradually increased from 50% to 100%.

[0122] It should be noted that when the system detects that the multi-source heterogeneous mean exceeds the preset threshold, the corresponding over-limit protection actions are executed respectively. For temperature over-limit, the heating relay is immediately turned off, the exhaust valve is fully opened to 100%, the fan speed is increased to 100%, and the backup pressure relief channel is started. For pressure over-limit, the humidification relay is turned off, and the exhaust valve opening is gradually increased from 50% to 100% by staged pressure relief to avoid the impact of the sudden pressure drop on the box structure. For low humidity over-limit, the humidification relay is turned on and runs at maximum power, and the exhaust valve is closed to 10% opening to maintain humidity. For high humidity over-limit, the humidification function is turned off and the exhaust valve is fully opened, and the fan runs at full speed to accelerate dehumidification. This embodiment takes differentiated measures according to the type and severity of the over-limit, taking into account both safety and equipment life.

[0123] Figure 4 A block diagram of an intelligent adjustment system for HAST equipment based on multi-source heterogeneous data of the present invention is shown.

[0124] like Figure 4 As shown, the second aspect of the present invention discloses a HAST device intelligent adjustment system 4 based on multi-source heterogeneous data, including a memory 41 and a processor 42. The memory includes a HAST device intelligent adjustment method program based on multi-source heterogeneous data. When the HAST device intelligent adjustment method program based on multi-source heterogeneous data is executed by the processor, the following steps are implemented:

[0125] The third aspect of the present invention provides a computer-readable storage medium, which includes a HAST device intelligent adjustment method program based on multi-source heterogeneous data. When the HAST device intelligent adjustment method program based on multi-source heterogeneous data is executed by a processor, the steps of the HAST device intelligent adjustment method based on multi-source heterogeneous data as described in any one of the above items are implemented.

[0126] In summary, the present invention provides a method, system and medium for intelligent adjustment of HAST equipment based on multi-source heterogeneous data. It collects heterogeneous data in real time based on temperature, humidity and pressure sensors, calculates the instantaneous change rate and sliding window mean through a differential algorithm, and matches the optimal cooling mode in combination with a preset rule base to solve the control lag and malfunction problems caused by traditional equipment relying on a single threshold. In the initialization phase, a patterned driver parameter template is loaded, and it is dynamically adjusted according to the real-time change rate during operation. The fan speed is optimized through a fuzzy PID algorithm, and an ARIMA time series model is introduced to predict future trends, so as to trigger exhaust or cooling actions in advance and avoid passive response. When the parameter mean exceeds the safety threshold, an emergency shutdown is performed in stages and the over-limit event is recorded to ensure the safety of the equipment and samples.

[0127] If the functions are implemented in the form of software function modules 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 invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0128] The foregoing description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Those skilled in the art will readily appreciate that various modifications and variations of the present invention are possible. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention are intended to be within the scope of protection of the present invention.

Claims

1. A HAST equipment intelligent adjustment method based on multi-source heterogeneous data, characterized in that: The method comprises: According to a preset collection cycle, multi-source heterogeneous data is collected based on preset sensors, wherein the multi-source heterogeneous data includes temperature values, humidity values, and pressure values; According to the multi-source heterogeneous data, a multi-source heterogeneous change rate and a multi-source heterogeneous mean are obtained; matching a cooling mode according to the multi-source heterogeneous change rate and the multi-source heterogeneous mean; Initializing driver parameters based on the cooling mode, wherein the driver parameters include exhaust valve opening, fan speed, heating relay switching time, and humidification relay switching time; adjusting driver parameters according to the multi-source heterogeneous change rate; Predicting a change trend based on the multi-source heterogeneous change rate and the multi-source heterogeneous mean, and using this to adjust driver parameters; Store the adjustment drive operation record in the log; If the multi-source heterogeneous mean exceeds a preset over-limit threshold, an over-limit mechanism is triggered to shut down the corresponding driver.

2. The HAST equipment intelligent adjustment method based on multi-source heterogeneous data according to claim 1 is characterized in that: The method of collecting multi-source heterogeneous data based on preset sensors according to a preset collection period is as follows: According to the preset collection cycle, the original values ​​of temperature, humidity and pressure in the box are collected synchronously through temperature sensors, humidity sensors and pressure sensors; According to the preset amount of data, a sliding window is determined to store the original value; According to the original value in the sliding window, a preset linear interpolation method is used to complete the window data; According to the window data, multi-source heterogeneous data is obtained based on a preset filtering algorithm.

3. The HAST equipment intelligent adjustment method based on multi-source heterogeneous data according to claim 1 is characterized in that: The multi-source heterogeneous data is used to obtain a multi-source heterogeneous change rate and a multi-source heterogeneous mean, specifically: Obtaining the multi-source heterogeneous instantaneous change rate based on the temperature, humidity and pressure data of the multi-source heterogeneous data and a preset differential algorithm; According to the temperature, humidity and pressure data of the multi-source heterogeneous data, based on a preset first window duration, a linear regression algorithm is used to obtain a multi-source heterogeneous trend change rate; According to the temperature, humidity and pressure data of the multi-source heterogeneous data, based on a preset second window duration, an arithmetic mean algorithm is used to obtain a multi-source heterogeneous mean; According to the multi-source heterogeneous mean, based on a preset normalization process, a multi-dimensional feature vector is obtained.

4. The HAST equipment intelligent adjustment method based on multi-source heterogeneous data according to claim 1 is characterized in that: Matching the cooling mode according to the multi-source heterogeneous change rate and the multi-source heterogeneous mean is specifically as follows: If the average temperature exceeds the target temperature, the temperature change rate exceeds the preset first temperature change threshold, and the pressure change rate is within the preset pressure stability range, it is determined to be in rapid cooling mode; If the temperature change rate is lower than a preset first temperature change threshold and the pressure average exceeds a preset first pressure threshold, it is determined to be a slow cooling mode; Or, if there is a sensitive material mark, it is determined to be a slow cooling mode; If the average humidity is lower than the preset humidity target, the humidity change rate is lower than the preset first humidity change threshold, and the temperature change rate is negative, it is determined to be in moisturizing cooling mode; Select a cooling mode based on the preset priority strategy.

5. The HAST equipment intelligent adjustment method based on multi-source heterogeneous data according to claim 4 is characterized in that: Also includes: When it is judged to be the rapid cooling mode, the exhaust valve opening is 100%, the fan speed is 100%, the heating relay is closed, and the humidification relay is closed; When the slow cooling mode is determined, the exhaust valve opening is 50%, the fan speed is 80%, and the heating relay maintains the minimum closing time. The exhaust valve opening and fan speed are gradually reduced according to the preset steps. When it is determined to be the moisturizing cooling mode, the exhaust valve is set to open 10% according to the preset moisturizing cycle, the fan is turned off, and the humidification relay is turned on.

6. The HAST equipment intelligent adjustment method based on multi-source heterogeneous data according to claim 1 is characterized in that: The adjusting of the driver parameters according to the multi-source heterogeneous change rate is specifically as follows: If the humidity change rate is higher than a preset second humidity change threshold, the closing time of the humidification relay is linearly shortened; If the pressure change rate is higher than a preset first pressure change threshold, shortening the exhaust valve opening according to a preset step; Based on the preset fuzzy PID algorithm, the fan speed is adjusted according to the deviation of the average temperature and average humidity from the target value.

7. A HAST equipment intelligent adjustment system based on multi-source heterogeneous data, characterized in that: The system includes a memory and a processor. The memory includes a HAST device intelligent adjustment method program based on multi-source heterogeneous data. When the HAST device intelligent adjustment method program based on multi-source heterogeneous data is executed by the processor, the following steps are implemented: According to a preset collection cycle, multi-source heterogeneous data is collected based on preset sensors, wherein the multi-source heterogeneous data includes temperature values, humidity values, and pressure values; According to the multi-source heterogeneous data, a multi-source heterogeneous change rate and a multi-source heterogeneous mean are obtained; matching a cooling mode according to the multi-source heterogeneous change rate and the multi-source heterogeneous mean; Initializing driver parameters based on the cooling mode, wherein the driver parameters include exhaust valve opening, fan speed, heating relay switching time, and humidification relay switching time; adjusting driver parameters according to the multi-source heterogeneous change rate; Predicting a change trend based on the multi-source heterogeneous change rate and the multi-source heterogeneous mean, and using this to adjust driver parameters; Store the adjustment drive operation record in the log; If the multi-source heterogeneous mean exceeds a preset over-limit threshold, an over-limit mechanism is triggered to shut down the corresponding driver.

8. The HAST equipment intelligent adjustment system based on multi-source heterogeneous data according to claim 7 is characterized in that: The method of collecting multi-source heterogeneous data based on preset sensors according to a preset collection period is as follows: According to the preset collection cycle, the original values ​​of temperature, humidity and pressure in the box are collected synchronously through temperature sensors, humidity sensors and pressure sensors; According to the preset amount of data, a sliding window is determined to store the original value; According to the original value in the sliding window, a preset linear interpolation method is used to complete the window data; According to the window data, multi-source heterogeneous data is obtained based on a preset filtering algorithm.

9. The HAST equipment intelligent adjustment system based on multi-source heterogeneous data according to claim 7 is characterized in that: The multi-source heterogeneous data is used to obtain a multi-source heterogeneous change rate and a multi-source heterogeneous mean, specifically: Obtaining the multi-source heterogeneous instantaneous change rate based on the temperature, humidity and pressure data of the multi-source heterogeneous data and a preset differential algorithm; According to the temperature, humidity and pressure data of the multi-source heterogeneous data, based on a preset first window duration, a linear regression algorithm is used to obtain a multi-source heterogeneous trend change rate; According to the temperature, humidity and pressure data of the multi-source heterogeneous data, based on a preset second window duration, an arithmetic mean algorithm is used to obtain a multi-source heterogeneous mean; According to the multi-source heterogeneous mean, based on a preset normalization process, a multi-dimensional feature vector is obtained.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: The computer-readable storage medium includes a HAST device intelligent adjustment method program based on multi-source heterogeneous data. When the HAST device intelligent adjustment method program based on multi-source heterogeneous data is executed by a processor, the steps of the HAST device intelligent adjustment method based on multi-source heterogeneous data as described in any one of claims 1 to 6 are implemented.

Images