Temperature transmitter controller based on PID control

Abstract

The invention discloses a temperature transmitter controller based on PID (Proportion Integration Differentiation) control, which relates to the technical field of temperature transmitter controllers and comprises an environmental data acquisition module, an environmental data storage and preprocessing module, a key feature extraction and fluctuation analysis module, a deep learning intelligent evaluation module and a self-adaptive dynamic temperature control module, the temperature transmitter controller carries out temperature detection on the musical instrument storage chamber according to a set detection period, real-time temperature data are obtained, a foundation is laid for subsequent data analysis and control, and it is guaranteed that the musical instrument storage chamber is stably maintained in a target temperature interval under the normal condition. PID intelligent temperature control, deep learning and adaptive adjustment are integrated, the musical instrument storage temperature is accurately controlled, musical instruments are prevented from being damaged, energy consumption is reduced, the service life of equipment is prolonged, the system is suitable for high-end musical instrument storage, museum protection and laboratory temperature control, and it is ensured that the system is stable and reliable for a long time.

Description

Technical Field

[0001] The present invention relates to the technical field of temperature transmitter controllers, and particularly relates to a temperature transmitter controller based on PID control. Background Art

[0002] A temperature transmitter controller based on PID control is an automatic control device for temperature measurement and regulation. It combines temperature sensing, signal transmission, and the PID (Proportional-Integral-Derivative) control algorithm to achieve high-precision temperature stability control. Its working principle is as follows: A temperature sensor (such as a thermocouple or a thermal resistor) collects the temperature signal of the measured environment and converts it into a standard electrical signal (such as 4 - 20 mA or 0 - 10 V) and transmits it to the PID controller through a transmitter. The PID controller compares the measured value with the set value, calculates the control quantity using proportional, integral, and differential operations, and outputs a control signal (such as PWM or an analog voltage) to regulate the actuator (such as an electric heater or a cooling system) to keep the temperature within the set range. The adaptive adjustment ability of the PID algorithm can compensate for external disturbances, improve the stability and accuracy of temperature control, and is widely used in industrial production, laboratory environments, and HVAC systems, etc.

[0003] A temperature transmitter controller based on PID control can be used for storing high-end musical instruments to ensure that the musical instruments maintain their sound quality and structural stability in the best environmental conditions for a long time. High-end wooden musical instruments (such as violins, pianos, guitars, cellos, etc.) are extremely sensitive to temperature and humidity changes. Excessive temperature may cause the wood to expand, the glue to melt, or the strings to become loose, while too low temperature may cause the wood to shrink, crack, or the tone to change. The PID temperature controller can be combined with a precision sensor to monitor the storage environment temperature in real time and perform dynamic adjustment through a heating or cooling system (such as a constant temperature air conditioner, a heating plate, or a refrigeration unit) to keep the temperature within the ideal range (usually 18 - 24 °C). Compared with traditional on-off temperature control systems, PID control can reduce temperature fluctuations through proportional, integral, and differential regulation, providing a more stable temperature control effect. In addition, by combining a humidity sensor and a humidification / dehumidification device, the humidity can also be controlled synchronously to prevent the wood from deforming or the strings from rusting, thereby effectively extending the lifespan of the musical instrument and maintaining its best tone.

[0004] The prior art has the following deficiencies: Temperature transmitter controllers in the prior art usually use a preset temperature detection period to obtain the temperature data of the musical instrument storage environment, in order to ensure monitoring accuracy, improve system stability, reduce energy consumption and avoid over-response of control. However, when the user frequently takes and places musical instruments, resulting in frequent opening and closing of the storage cabinet or storage room, the ambient temperature will change rapidly. If the controller still uses a fixed detection period, it may fail to detect the sudden temperature change in time due to response lag, and only start to adjust until the next detection period, resulting in serious consequences. Sudden temperature changes may cause the wooden structure to expand, contract or even crack. Especially for precious handmade violins, piano soundboards, etc., large temperature differences will affect the sound quality and even cause irreversible damage. In addition, the temperature rise will cause the metal strings to expand, and the temperature drop will cause the strings to contract, the pitch to shift, and even the strings to break, affecting the performance quality and requiring frequent tuning. Therefore, in the case of drastic temperature changes, the traditional fixed detection period mode has obvious limitations, which may endanger the structural integrity, sound quality stability and service life of musical instruments.

[0005] The above information disclosed in the background art section is only used to enhance the understanding of the background of the present disclosure. Therefore, it may include information that does not constitute the prior art known to those of ordinary skill in the art. Summary of the Invention

[0006] The object of the present invention is to provide a temperature transmitter controller based on PID control, which can accurately monitor and dynamically adjust the temperature of the musical instrument storage room through PID intelligent temperature control, deep learning, adaptive sampling and elastic temperature control window, to avoid damages such as cracking of wooden musical instruments and breaking of strings caused by response lag. When the temperature changes suddenly, the sampling period is shortened, and the threshold is relaxed after stabilization, reducing frequent start and stop, reducing energy consumption and extending the equipment life. It is widely applicable to fields such as high-end musical instrument storage, museum protection, precision laboratories, etc., to ensure the long-term stability and reliability of the temperature control system, so as to solve the problems in the above background art.

[0007] To achieve the above object, the present invention provides the following technical solution: A temperature transmitter controller based on PID control, comprising an environmental data acquisition module, an environmental data storage and preprocessing module, a key feature extraction and fluctuation analysis module, a deep learning intelligent evaluation module, and an adaptive dynamic temperature control module: The environmental data acquisition module, the temperature transmitter controller performs temperature detection on the musical instrument storage room according to a predetermined detection period, obtains real-time temperature data, lays a foundation for subsequent data analysis and control, and ensures that the musical instrument storage room is stably maintained within the target temperature range under normal circumstances; The environmental data storage and preprocessing module stores all the acquired environmental data in chronological order to form a data set, and preprocesses the environmental data in the data set to ensure the reliability and consistency of the data used in subsequent model analysis; The key feature extraction and fluctuation analysis module, after completing data preprocessing, extracts key features reflecting the rapid change trend of storage room temperature from the preprocessed environmental data set, and analyzes the extracted key features under the detection window to quantify the current ambient temperature fluctuation amplitude; The deep learning intelligent evaluation module inputs the analyzed key features into the pre-trained deep learning model to intelligently evaluate the current temperature change status of the storage room; The adaptive dynamic temperature control module captures the temperature change trend in real time by dynamically adjusting the temperature sampling frequency when the deep learning model evaluation results show that the temperature in the storage room is changing rapidly. At the same time, it adaptively adjusts the response threshold based on the temperature fluctuation amplitude to create a flexible temperature control window. It actively reduces the threshold when the fluctuation is severe and quickly triggers precise adjustment. It automatically relaxes the threshold after the temperature tends to stabilize to avoid energy waste and equipment loss caused by repeated actions.

[0008] Preferably, the specific steps of storing all acquired environmental data in chronological order and forming a data set are as follows: First, after the temperature transmitter controller obtains the environmental data, all the data are first stored in chronological order to form a structured data set to ensure the integrity and traceability of the data; Next, data preprocessing is performed on the environmental data in the data set, specifically including the following steps: 1. Data cleaning: Identify and remove outliers and missing values, and use interpolation methods to fill in data gaps to prevent model misjudgment; 2. Denoising and smoothing: Remove noise through methods such as sliding mean filtering or Kalman filtering to reduce short-term jitter in temperature data and improve data stability; 3. Unit normalization and standardization: ensure that data from different sources have the same scale to facilitate subsequent analysis and modeling; 4. Time series alignment: For multi-sensor data, synchronize the data according to a unified time step to ensure that the data set remains consistent in the time dimension.

[0009] Preferably, key features reflecting the trend of rapid changes in the storage room temperature are extracted from the preprocessed environmental data set, the extracted features including the degree of influence of the switching state of the storage room door on the temperature fluctuation and the abnormal situation of the heat release rate of objects inside the storage room. The degree of influence of the switching state of the storage room door on the temperature fluctuation and the abnormal situation of the heat release rate of objects inside the storage room are analyzed under the detection window, and a gated disturbance sensitive reference value and an environmental heat capacity release abnormal reference value are generated respectively. The current ambient temperature fluctuation amplitude is quantified by the gated disturbance sensitive reference value and the environmental heat capacity release abnormal reference value.

[0010] Preferably, the specific steps for analyzing the influence degree of the opening and closing state of the storage room door on temperature fluctuations and generating a door control disturbance sensitivity reference value are as follows: First, analyze the change in the opening and closing state of the storage room door, calculate the influence intensity of the door opening and closing disturbance on temperature, and define a door control disturbance influence factor in combination with factors such as the door opening and closing frequency, door opening duration, door opening angle, and indoor-outdoor temperature difference. The calculation expression is as follows: , where is the door control disturbance influence factor, is the number of times the door opens and closes within the detection window, indicating the frequency of door opening and closing, is the total duration that the door remains open within the detection window, is the door opening angle, is the indoor temperature, is the outdoor temperature, , and are all door switch influence weight parameters, controls the influence of the number of switch operations on door control disturbance, controls the influence of the door opening time on door control disturbance, controls the influence of the temperature difference on door control disturbance, , and are all non-linear exponential adjustment parameters, controls the non-linear growth of the number of door switch operations , controls the influence of the door opening duration on the disturbance, controls the amplification degree of the temperature difference , is the function steepness adjustment parameter, is the natural base; After obtaining the door control disturbance influence factor , further calculate its direct influence on the temperature change of the storage room to generate a door control disturbance sensitivity reference value. The generation formula is as follows: , where is the door control disturbance sensitivity reference value, is the second derivative of the temperature field, is the convective heat transfer rate, is the specific heat capacity of air, is the air volume of the storage room, is the weight factor, and are both adjustment parameters, controlling the overall weights of the temperature gradient influence and the convective heat transfer influence respectively, is the power parameter, is the scaling factor, is the adjustment factor.

[0011] Preferably, the specific steps for analyzing the abnormal situation of the heat release rate of the objects inside the storage room to generate the abnormal reference value of the environmental heat capacity release are as follows: First, calculate the offset of the instantaneous heat release rate of the objects inside the storage room. The walls, floor, storage cabinets, and the musical instruments themselves inside the storage room all have heat capacity effects. Under normal conditions, the heat release rate of the objects will follow the heat exchange law, and the heat release rate of the objects is calculated by combining Fourier's law of heat conduction with convective heat transfer between air. The calculation expression is as follows: , where, is the instantaneous heat release rate of the object, is the thermal conductivity of the object, is the surface area of the object, is the temperature gradient between the surface of the object and the air, is the convective heat transfer coefficient, is the effective contact area for convective heat transfer between the object and the air, is the non-linear exponent of convective heat transfer; Under normal circumstances, the heat release of the storage room should be balanced. Even if the temperature changes slightly, the heat capacity effect of the objects will buffer the temperature fluctuations. However, when the heat release rate exceeds its normal physical constraint range, it indicates abnormal temperature changes. The non-equilibrium is described by the following formula, and the calculation expression is as follows: , where, is the heat release non-equilibrium index, is the heat release rate measured in real time by the sensor, is the theoretical heat release rate calculated based on the normal heat exchange model of the environment, is the weight factor, is the regularization parameter, is the normalization coefficient, is the damping index; Based on the instantaneous heat release rate of the object and the heat release non-equilibrium index , generate the abnormal reference value of the environmental heat capacity release, which is used to quantify the intensity of the abnormal environmental heat capacity release. The generation formula is as follows: , where, is the abnormal reference value of the environmental heat capacity release, is the normalization adjustment coefficient, is the scaling factor, is the short-term change influence coefficient, is the actual heat release rate at the th time point within the detection window, is the heat release rate at the previous time point within the detection window, is the number of time points within the detection window, is the change rate weight.

[0012] Preferably, the gated perturbation sensitive reference value and the environmental heat capacity release anomaly reference value after analysis are input into a pre-trained deep learning model. The deep learning model generates a temperature fluctuation anomaly coefficient, and the current temperature change state of the storage chamber is intelligently evaluated through the temperature fluctuation anomaly coefficient.

[0013] Preferably, when the deep learning model intelligently evaluates the current temperature change state of the storage chamber, the temperature fluctuation anomaly coefficient generated is compared and analyzed with a pre-set temperature fluctuation anomaly coefficient reference threshold, and the current temperature change of the storage chamber is divided as follows: If the temperature fluctuation anomaly coefficient is greater than the pre-set temperature fluctuation anomaly coefficient reference threshold, the current temperature of the storage chamber is classified as a rapid change state; if the temperature fluctuation anomaly coefficient is less than or equal to the pre-set temperature fluctuation anomaly coefficient reference threshold, the current temperature of the storage chamber is classified as a stable change state.

[0014] Preferably, when the evaluation result of the deep learning model shows that the temperature of the storage chamber is changing rapidly, the specific steps for dynamically adjusting the temperature sampling frequency and adaptively adjusting the response threshold based on the temperature fluctuation amplitude are as follows: When the evaluation result of the deep learning model shows that the temperature of the storage chamber is changing rapidly, an adaptive sampling strategy is adopted to adjust the temperature sampling frequency in real time to enhance the response ability of the temperature control system. The calculation expression is as follows: , where is the adjusted temperature sampling frequency, is the default basic sampling frequency, is the sampling frequency exponential adjustment coefficient, which controls the growth rate of the sampling frequency, is the exponential adjustment factor, is the natural base, is the temperature fluctuation anomaly coefficient, is the temperature fluctuation anomaly coefficient reference threshold, is a very small number to prevent the denominator from being zero, is the temperature change trend term, is the smoothing factor; While dynamically adjusting the sampling frequency, further optimize the temperature control response logic. Through the "elastic temperature control window" mechanism, adaptively adjust the temperature control trigger threshold, and the adjustment formula is as follows: , where, is the adjusted temperature control trigger threshold, is the default basic temperature control threshold, is the response threshold shrinkage coefficient, is the bidirectional non-linear control term, using the hyperbolic tangent function for smooth convergence, is the time decay term, is the time decay intensity factor, is the time scale adjustment parameter, is the time step.

[0015] In the above technical solution, the technical effects and advantages provided by the present invention are: By introducing an intelligent temperature control strategy based on PID control, combining deep learning, adaptive sampling frequency adjustment and elastic temperature control window, the present invention effectively solves the problem of response lag of traditional temperature control systems with fixed detection cycles, and realizes precise monitoring and dynamic adjustment of the temperature in the musical instrument storage room. The beneficial effects of the present invention are as follows: By collecting, preprocessing and feature extracting environmental data in real time, it can accurately identify abnormal fluctuations in the temperature of the storage room, and use deep learning to intelligently evaluate the temperature change trend, ensuring that the temperature control system can dynamically shorten the sampling period and quickly respond and adjust in case of sudden temperature fluctuations, avoiding irreversible damages such as thermal expansion and contraction, cracking, paint layer damage, and string breakage of wooden musical instruments caused by temperature change lag. In addition, the elastic temperature control window mechanism proposed by the present invention actively reduces the control threshold when the temperature changes violently, improves the temperature control accuracy, automatically relaxes the threshold after the temperature stabilizes, reduces unnecessary control actions, avoids frequent start and stop of the temperature control system, reduces energy consumption and equipment loss, thereby improving the energy efficiency of the system and the service life of the temperature control equipment while ensuring the storage safety of musical instruments. The present invention has wide application value in the fields of high-end musical instrument storage, constant temperature protection of museum cultural relics, and environmental control of precision laboratories, etc., and can effectively improve the intelligent level of the temperature control system and ensure the long-term stability and reliability of the temperature environment. Description of the Drawings

[0016] 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 to be used in the embodiments. Obviously, the drawings described below are only some embodiments recorded in the present invention. For those of ordinary skill in the art, other drawings can also be obtained according to these drawings.

[0017] Figure 1This is a schematic diagram of the modules of a temperature transmitter controller based on PID control according to the present invention. Specific embodiments

[0018] Example embodiments will now be described more fully with reference to the accompanying drawings. However, the example embodiments can be implemented in various forms and should not be construed as limited to the examples set forth herein; rather, these example embodiments are provided so that this disclosure will be more thorough and complete, and will fully convey the concept of the example embodiments to those skilled in the art.

[0019] The present invention provides a Figure 1 temperature transmitter controller based on PID control as shown, including an environmental data acquisition module, an environmental data storage and preprocessing module, a key feature extraction and fluctuation analysis module, a deep learning intelligent evaluation module, and an adaptive dynamic temperature control module: Environmental data acquisition module, the temperature transmitter controller performs temperature detection on the musical instrument storage room according to a predetermined detection period, obtains real-time temperature data, lays a foundation for subsequent data analysis and control, and ensures that the musical instrument storage room is stably maintained within the target temperature range under normal circumstances; The setting of this fixed period is designed to enable the system to obtain temperature data in a timely manner under normal circumstances and not cause waste of energy consumption and computing resources due to overly frequent detections. At this time, the controller will enable the temperature sensor or retrieve environmental parameters regularly according to the pre-set sampling frequency, and record the current temperature.

[0020] Environmental data storage and preprocessing module, stores all the acquired environmental data (such as temperature, humidity, door switch status, timestamp, etc.) in chronological order to form a data set, and preprocesses the environmental data in the data set to ensure the reliability and consistency of the data used in subsequent model analysis; The specific steps of storing all the acquired environmental data in chronological order to form a data set are as follows: First, after the temperature transmitter controller acquires environmental data, all the data is first stored in chronological order to form a structured data set to ensure the integrity and traceability of the data; Next, data preprocessing is performed on the environmental data in the data set, which specifically includes the following steps: (1) Data cleaning: Identify and remove outliers (such as extreme data points caused by sensor failures) and missing values, and use interpolation methods to fill in data gaps to prevent model misjudgment; (2) Denoising and smoothing: Remove noise through methods such as moving average filtering or Kalman filtering, reduce short-term jitter in temperature data, and improve data stability; (3) Unit normalization and standardization: Ensure that data from different sources (such as temperature, humidity, time) have the same scale to facilitate subsequent analysis and modeling; (4) Time series alignment: For multi-sensor data, perform synchronization processing according to a unified time step to ensure the consistency of the data set in the time dimension.

[0021] This series of preprocessing steps ensures that the environmental data used in the subsequent deep learning model analysis has high accuracy, consistency, and availability, thereby improving the accuracy of temperature change trend prediction and the stability of system control.

[0022] In this process, the system will mark or index the data obtained at each time point or detection cycle so that it can be quickly retrieved and used in subsequent analysis. The role of this step is to form a continuously updated historical data warehouse, enabling the model or algorithm to identify and learn temperature change patterns with the help of long-term data accumulation. Without such a systematic and complete historical data record, the subsequent deep learning model will not be able to make in-depth judgments on "sudden rapid changes" or "stable periods".

[0023] In the preprocessing stage, the system will perform a series of processing on the original data, including noise removal, outlier detection, missing value filling, and data smoothing. For example, if the temperature sensor is occasionally affected by electromagnetic interference and generates extreme error data, it can be removed or corrected through outlier detection and interpolation algorithms; if data is missing in some periods, the system can also fill it through interpolation or statistical methods based on adjacent time periods. The core significance of preprocessing is to ensure that the data used in subsequent model analysis has higher reliability and consistency, thereby reducing the misjudgment rate or control misoperations caused by noise.

[0024] After completing the data preprocessing, the key feature extraction and fluctuation analysis module extracts the key features reflecting the rapid change trend of the storage room temperature from the preprocessed environmental data set, and analyzes the extracted key features under the detection window to quantify the current environmental temperature fluctuation amplitude; Extract the key features reflecting the rapid change trend of the storage room temperature from the preprocessed environmental data set. The extracted features include the degree of influence of the opening and closing state of the storage room door on temperature fluctuations and the abnormal situation of the heat release rate of the objects inside the storage room. Analyze the degree of influence of the opening and closing state of the storage room door on temperature fluctuations and the abnormal situation of the heat release rate of the objects inside the storage room under the detection window, and generate the door control disturbance sensitivity reference value and the environmental heat capacity release anomaly reference value respectively. Quantify the current environmental temperature fluctuation amplitude through the door control disturbance sensitivity reference value and the environmental heat capacity release anomaly reference value.

[0025] The influence of the door switch state on the temperature fluctuation is aggravated, which usually indicates that the current temperature of the storage room is changing rapidly. From the perspective of temperature stability, the internal environment of the storage room usually relies on the wall, air heat capacity and temperature control system to maintain a relatively constant temperature. When the door is opened frequently or left open for a long time, the outside air will quickly exchange heat with the indoor air, resulting in a sudden change in temperature. The rate of temperature change is positively correlated with the door switch frequency, the door opening time and the temperature difference between indoor and outdoor. When the door switch frequency increases or the door is opened for a long time, the temperature disturbance amplitude will increase, directly leading to rapid temperature fluctuations in a short period of time. For example, in the summer when the outside temperature is high, opening the door will introduce a large amount of hot air, causing the temperature of the storage room to rise rapidly; in winter, the temperature may drop sharply due to the entry of cold air. In addition, the air flow in the storage room is low and the heat exchange rate is slow. Therefore, when the door is closed, the internal temperature may continue to fluctuate for a period of time due to inertia, causing the temperature change trend to further intensify. Therefore, when the influence of the door control disturbance increases, it usually indicates that the temperature of the storage room has entered a state of violent fluctuations. It is necessary to increase the temperature sampling frequency and adjust the temperature control strategy in time to avoid temperature out of control and affect the safety of musical instrument storage.

[0026] The specific steps for analyzing the influence of the open and close state of the storage room door on the temperature fluctuation under the detection window to generate the gated disturbance sensitive reference value are as follows: First, the change of the opening and closing state of the storage room door is analyzed to calculate the influence of the door opening and closing disturbance on the temperature. Combining the door opening and closing frequency, door opening duration, door opening angle and indoor and outdoor temperature difference factors, the door control disturbance influence factor is defined to represent the disturbance intensity of the door state on the temperature change. The calculation expression is as follows: , where is the gating perturbation factor, It is the number of times the door in the detection window is opened and closed, indicating the frequency of the door opening and closing. is the total time the door remains open within the detection window. Longer door opening time results in stronger heat exchange. is the door opening angle, the value range is The larger the door opening angle, the more intense the air circulation. is the indoor temperature, is the outdoor temperature, , as well as These are the weight parameters that affect the door switch. The influence of control switching times on gate disturbance, Control the effect of gate opening time on gate disturbance, Control the influence of temperature difference on gating perturbation to highlight the dominant role of temperature difference in gating perturbation. , as well as are all non - linear exponential adjustment parameters, control the number of times the door opens and closes of the non - linear growth, control the duration of the door open on the influence of disturbances, control the temperature difference of the amplification degree, is the function steepness adjustment parameter, the function controls the change rate of the influence of the door angle on disturbances, is the natural base; By calculating factors such as the opening and closing frequency of the door, the duration of the door open, the opening angle of the door, and the indoor - outdoor temperature difference, a door - control disturbance influence factor is generated , which is used to measure the driving force of door control on the change of environmental temperature. This step uses a non - linear power function, exponential transformation, and a smoothing function to ensure that the influence is small under low - disturbance conditions, while being able to significantly amplify the temperature change trend under high - disturbance conditions, providing accurate data support for the subsequent dynamic adjustment of the sampling frequency of the temperature control system and the intelligent adjustment of the temperature control strategy.

[0027] After obtaining the door - control disturbance influence factor , further calculate its direct influence on the temperature change of the storage room to generate a door - control disturbance sensitivity reference value. Considering the instantaneous acceleration of temperature change, the local heat diffusion rate, and the short - term non - steady - state heat flux disturbance, the formula is as follows: , where, is the door - control disturbance sensitivity reference value, is the second - order derivative of the temperature field, representing the spatial non - uniformity of temperature change and reflecting the severity of the local temperature gradient, is the convective heat transfer rate, representing the amount of convective heat transfer of air caused by the opening of the door, and is used to measure how the opening and closing of the door affect the heat exchange rate of air, is the specific heat capacity of air, representing the heat required for unit mass of air to absorb or release a 1K temperature change, and affects the response speed of temperature change, is the volume of air in the storage room, is the weight factor, used to adjust the influence of so that it is more sensitive to large disturbances and less responsive to small disturbances, and are both adjustment parameters, respectively controlling the overall weights of the influence of temperature gradient and convective heat transfer, is the power parameter, adjusting the non - linear degree of the influence of the second - order temperature gradient on the door - control disturbance sensitivity reference value , is the scaling factor, controlling The influence in the exponential term makes the perturbation influence smoother. It is an adjustment factor that regulates the influence of the convective heat transfer calculation part to adapt to storage rooms of different scales.

[0028] By comprehensively analyzing the non-uniformity of the temperature field and the influence of air convective heat transfer, the contribution degree of the gating perturbation to the temperature fluctuation of the storage room is quantified, thereby generating a gating perturbation sensitivity reference value. This step can not only accurately capture the drastic temperature changes caused by the gating perturbation, but also adjust the influence weight through the exponential term, enabling the system to remain stable in the face of small perturbations, and thus quickly respond during drastic temperature fluctuations, improving the intelligence and adaptability of the temperature control system.

[0029] The larger the gating perturbation sensitivity reference value generated after analyzing the influence degree of the opening and closing state of the storage room door on the temperature fluctuation under the detection window, the faster the current temperature of the storage room is changing. Conversely, it indicates that the temperature change is relatively stable.

[0030] The gating perturbation sensitivity reference value measures the influence of the gating state on the temperature fluctuation by comprehensively analyzing the door opening and closing frequency, door opening duration, indoor-outdoor temperature difference, and the corresponding temperature change rate. Within the monitoring window, if the gating perturbation sensitivity reference value is high, it means the door is frequently opened or left open for a long time, and this has led to significant temperature changes (such as a sudden increase or decrease in temperature), which implies that there is strong heat exchange between the indoor air and the external environment, causing the temperature to fluctuate violently in a short period. Therefore, the higher the gating perturbation sensitivity reference value, the faster the temperature is changing. Conversely, if the gating perturbation sensitivity reference value is low, it means the opening and closing of the door has little influence on the temperature, or although the door is opened, the indoor temperature has not changed significantly, which usually means the temperature of the storage room remains relatively stable.

[0031] An abnormal change in the rate of heat release from the objects inside the storage room can indicate that the current temperature of the storage room is changing rapidly. The reason is that the objects inside the storage room (such as walls, floors, storage cabinets, and musical instruments themselves) have a heat capacity effect and can usually absorb or release heat to make the change in the ambient temperature tend to be gentle. However, when the rate of heat release from these objects shows abnormal fluctuations, it indicates that the way of heat transfer has changed drastically, which usually directly leads to a rapid change in the ambient temperature. For example, under normal circumstances, the wooden storage cabinet and the musical instrument itself slowly release or absorb heat and can adjust the local ambient temperature. However, if the rate of heat release from them increases significantly during a certain period (such as abnormal operation of the air conditioner or heating system, sudden influx of external hot air), it means that the thermal balance of the storage room is broken and the temperature rises rapidly. Similarly, if the rate of heat absorption by the object suddenly increases (such as the entry of cold air, rapid decrease in humidity leading to accelerated evaporation heat absorption), the temperature of the storage room may drop suddenly. Therefore, the abnormal change in the rate of heat release reflects the drastic fluctuation of the internal energy exchange in the storage room, and the rapid change in the energy exchange rate is necessarily accompanied by a rapid change in temperature. Therefore, it can be used as an important indicator to monitor the drastic fluctuation of the ambient temperature, helping the intelligent temperature control system to respond in advance and optimize the adjustment strategy.

[0032] The specific steps to analyze the abnormal situation of the rate of heat release from the objects inside the storage room to generate the abnormal reference value of the ambient heat capacity release are as follows: First, calculate the offset of the instantaneous heat release rate of the objects inside the storage room. The walls, floors, storage cabinets, and musical instruments inside the storage room all have a thermal capacity effect. Under normal conditions, the rate of heat release from the objects will follow the law of heat exchange, and the rate of heat release from the objects is calculated by combining Fourier's law of heat conduction with convective heat transfer between the air. The calculation expression is as follows: , where is the instantaneous heat release rate of the object, is the thermal conductivity of the object, which determines the internal heat conduction ability of the object, is the surface area of the object, which is directly related to the heat exchange ability of the object, is the temperature gradient between the surface of the object and the air, is the convective heat transfer coefficient, which determines the heat transfer ability of the air layer to the object, is the effective contact area for convective heat transfer between the object and the air, is the non-linear exponent of convective heat transfer; Function of the formula: The first term reflects the internal thermal conductivity characteristics of the object, that is, how the object releases heat outward through the thermal conductivity of its own material.

[0033] The second term Reflects the heat transfer process between the object surface and the air, which is affected by air fluidity (such as air conditioner wind speed, door and window states, etc.), and is an important factor affecting the rapid temperature change in the storage room.

[0034] If the heat release rate of the storage room undergoes a non-linear mutation (such as far exceeding the normal range of material thermal conductivity and convective heat transfer characteristics), it indicates that the environmental temperature has changed violently in a short period of time, which is a direct signal of abnormal release of environmental heat capacity.

[0035] Under normal circumstances, the heat release in the storage room should be balanced. Even if the temperature changes slightly, the heat capacity effect of the object will buffer the temperature fluctuation. However, when the heat release rate exceeds its normal physical constraint range, it indicates abnormal temperature change. The non-equilibrium is described by the following formula, and the calculation expression is as follows: , where is the heat release non-equilibrium index, is the heat release rate measured in real time by the sensor, is the theoretical heat release rate calculated according to the normal heat exchange model of the environment, is the weight factor to emphasize the influence of larger deviations on abnormal changes, is the regularization parameter to avoid the amplification of abnormal values caused by too small denominator, is the normalization coefficient, which is adjusted according to historical data to adapt to different storage environments, is the damping index to control the growth rate of the denominator Function of the formula: The numerator: calculates the difference between the actual heat release rate and the theoretical heat release rate, and exponentially amplifies it, so that larger abnormal values have higher sensitivity.

[0036] The denominator: introduces the normalization factor to ensure that objects with different heat capacities are not amplified or reduced by the absolute heat value during the calculation process.

[0037] Overall exponential processing: If the value is large, it indicates that abnormal heat capacity release has occurred in the storage room, usually meaning that the storage environment temperature is changing violently.

[0038] Based on the instantaneous heat release rate of the object and the heat release non-equilibrium index , an abnormal reference value for environmental heat capacity release is generated to quantify the intensity of abnormal environmental heat capacity release. The generation formula is as follows: , where is the abnormal reference value of ambient heat capacity release, is the normalization adjustment coefficient, which is used to match the distribution range of historical data. is a scaling factor used to control the increase in the abnormal reference value of ambient heat capacity release. It is the short-term change influence coefficient, which adjusts the heat release change rate in a short period of time to the abnormal reference value of the ambient heat capacity release Contribution is within the detection window, The actual heat release rate at a time point is is the heat release rate at the previous time point within the detection window, is the number of time points in the detection window, is the rate-of-change weight, used to emphasize larger fluctuations.

[0039] Formula function: Item 1 Emphasize the main contribution of ambient heat capacity anomalies to the reference value, and magnify them to make larger anomalies easier to detect.

[0040] Item 2 Calculate the trend of heat release in a short period of time. If the release rate of the object continues to be unstable, the abnormal reference value of the ambient heat capacity release Further improvement.

[0041] Final ambient heat capacity release abnormal reference value The larger the value, the more abnormal the heat exchange inside the storage room is, which means that the current temperature of the storage room is changing rapidly. At this time, the temperature control system can automatically adjust the sampling frequency or start a precise temperature control strategy to ensure the stability of the storage environment.

[0042] The larger the abnormal reference value of the environmental heat capacity release generated after analyzing the abnormal situation of the heat release rate of the objects inside the storage room, the faster the current temperature of the storage room is changing. On the contrary, it indicates that the temperature is in a stable state. The core of calculating this reference value lies in monitoring the abnormal situation of the heat release rate of the objects inside the storage room within the monitoring window, that is, detecting the degree to which the rate of heat absorption or release by the objects deviates from the normal trend. In an ideal stable environment, the heat capacity effects of the walls, storage cabinets, musical instruments themselves, etc. inside the storage room can buffer the temperature changes, making the temperature change relatively slowly and the abnormal reference value of the environmental heat capacity release relatively low. However, when the external environment suddenly changes (such as the door being opened, the air conditioner malfunctioning, or sudden influx of external heat flow), the rate of heat release or absorption by the objects will fluctuate violently, breaking the thermal balance and causing the temperature to rise or fall sharply in a short period of time. At this time, this reference value will increase significantly. Therefore, when the abnormal reference value of the environmental heat capacity release is larger, it means that the heat transfer inside the storage room is abnormally active and the temperature is fluctuating rapidly; when the reference value is smaller, it indicates that the heat exchange is at a normal level and the temperature is relatively stable.

[0043] The deep learning intelligent evaluation module inputs the analyzed key features into a pre-trained deep learning model to intelligently evaluate the current temperature change state of the storage room; Input the analyzed door control perturbation sensitive reference value and the abnormal reference value of the environmental heat capacity release into a pre-trained deep learning model. Generate a temperature fluctuation abnormal coefficient through the deep learning model, and use the temperature fluctuation abnormal coefficient to intelligently evaluate the current temperature change state of the storage room.

[0044] The pre-trained deep learning model refers to a neural network model that has been trained with a large amount of historical data and has learned to recognize specific patterns and rules before being formally applied. In this scenario, this deep learning model is offline trained with a large amount of environmental data such as temperature, humidity, door control perturbation, and abnormal heat capacity release, enabling it to learn the trends, mutation patterns, and relationships between environmental factors affecting the temperature change of the storage room, so as to quickly and accurately evaluate the current temperature fluctuation state during actual operation. This model usually adopts time series prediction networks (such as long short-term memory network LSTM, temporal convolutional network TCN, or Transformer transformation model) because these networks are particularly suitable for capturing the changing patterns of environmental data with strong time dependence. During the training process, the model will use the labeled temperature change data to continuously optimize the parameters through the backpropagation algorithm, enabling it to accurately distinguish between "normal temperature changes" and "abnormal temperature mutations". In addition, this deep learning model will also comprehensively consider the door control perturbation sensitive reference value, the abnormal reference value of the environmental heat capacity release, and other key temperature features, so as to establish a multi-variable associated prediction system and improve the perception ability of sudden temperature anomalies.

[0045] After the model training is completed, in actual applications, it serves as an online inference system that receives input data such as gating perturbations, heat capacity release anomalies, and temperature fluctuation rates in real time and automatically calculates the temperature fluctuation anomaly coefficient. This temperature fluctuation anomaly coefficient is a numerical risk assessment indicator that represents the severity of the current temperature change and the possible future fluctuation amplitude. For example, if the model identifies frequent gating opening and closing, a large temperature difference between the inside and outside of the storage room, and an intensified temperature fluctuation within a short period, the temperature fluctuation anomaly coefficient will increase significantly. The system will immediately trigger a higher frequency of data sampling and adjust the response strategy of the temperature control equipment. If the model determines that the current temperature fluctuation is within the normal range, it will maintain the regular monitoring cycle to avoid unnecessary energy consumption and equipment wear. This intelligent temperature control assessment method is more accurate than the traditional fixed threshold judgment method because it can learn the influence of complex environmental factors from historical data, avoid misjudgment, improve the adaptive ability of the temperature control system, and thus achieve faster and more accurate temperature control adjustments in case of sudden temperature changes, ensuring the stability and safety of the musical instrument storage environment.

[0046] The deep learning model is not limited here and can realize the sensitive reference value of gating perturbation and the abnormal reference value of environmental heat capacity release to comprehensively analyze and generate the temperature fluctuation anomaly coefficient Any deep learning model can be used. To implement the technical solution of the present invention, the present invention provides a specific implementation method; The temperature fluctuation anomaly coefficient is generated according to the following formula: , where and are the preset proportional coefficients of the sensitive reference value of gating perturbation and the abnormal reference value of environmental heat capacity release respectively, and and are both greater than 0.

[0047] The preset proportional coefficients (PresetProportionalCoefficients) refer to the weight factors and set for different influencing factors (the sensitive reference value of gating perturbation and the abnormal reference value of environmental heat capacity release and ) when calculating the temperature fluctuation anomaly coefficient

[0048] Specifically: h represents weight: If experimental or data analysis shows that the gating perturbation has a greater impact on temperature changes, then will be higher, meaning is more inclined to be affected by gating perturbations.

[0049] represents weight: If the abnormal heat capacity release in the storage environment (such as sudden changes in air conditioner temperature, heat absorption / dissipation of the wall) is the main influencing factor, then will be higher, making more affected by influence.

[0050] Preset proportionality coefficient and values are usually determined based on experimental tests, deep learning model training, or adaptive optimization algorithms, rather than being fixed. They may be dynamically adjusted according to environmental changes or feedback from machine learning models to improve the accuracy and adaptability of the system.

[0051] From the temperature fluctuation anomaly coefficient, the greater the gating perturbation sensitivity reference value generated by analyzing the influence degree of the opening and closing state of the storage room door on temperature fluctuation under the detection window, and the greater the environmental heat capacity release anomaly reference value generated by analyzing the abnormal situation of the heat release rate of the objects inside the storage room, the greater the temperature fluctuation anomaly coefficient generated by the intelligent evaluation of the current temperature change state of the storage room through a pre-trained deep learning model, indicating that the probability of the current temperature in the storage room being in a rapid change state is greater. Conversely, it indicates that the probability of the current temperature in the storage room being in a rapid change state is smaller.

[0052] Compare and analyze the temperature fluctuation anomaly coefficient generated by the intelligent evaluation of the current temperature change state of the storage room through a pre-trained deep learning model with the preset temperature fluctuation anomaly coefficient reference threshold, and divide the current temperature change of the storage room. The division steps are as follows: If the temperature fluctuation anomaly coefficient is greater than the preset temperature fluctuation anomaly coefficient reference threshold, then divide the current temperature of the storage room into a rapid change state; if the temperature fluctuation anomaly coefficient is less than or equal to the preset temperature fluctuation anomaly coefficient reference threshold, then divide the current temperature of the storage room into a stable change state.

[0053] Adaptive dynamic temperature control module. When the evaluation result of the deep learning model shows that the temperature in the storage room is changing rapidly, by dynamically adjusting the temperature sampling frequency, it can capture the temperature change trend in real time. At the same time, it adaptively adjusts the response threshold based on the temperature fluctuation amplitude to create an "elastic temperature control window". When the fluctuation is severe, it actively reduces the threshold to quickly trigger precise adjustment; when the temperature tends to be stable, it automatically relaxes the threshold to avoid energy consumption waste and equipment loss caused by repeated actions. When the evaluation result of the deep learning model shows that the temperature in the storage room is changing rapidly, the specific steps of dynamically adjusting the temperature sampling frequency and adaptively adjusting the response threshold based on the temperature fluctuation amplitude are as follows: When the evaluation result of the deep learning model shows that the temperature in the storage room is changing rapidly, an adaptive sampling strategy is adopted to adjust the temperature sampling frequency in real time to enhance the response ability of the temperature control system. When the temperature fluctuates violently, the sampling frequency is increased to capture the temperature change trend more real-time; when the temperature is stable, the sampling frequency is decreased to reduce the computational burden and energy consumption. The calculation formula is as follows: , where is the adjusted temperature sampling frequency, is the default basic sampling frequency, is the sampling frequency exponential adjustment coefficient, which controls the growth rate of the sampling frequency, is the exponential adjustment factor, is the natural base, is the temperature fluctuation anomaly coefficient, is the reference threshold of the temperature fluctuation anomaly coefficient, is an extremely small number to prevent the denominator from being zero, is the temperature change trend term, representing the first derivative (gradient) of the temperature fluctuation anomaly coefficient , that is, the change rate of the temperature anomaly coefficient, is the smoothing factor; Through the exponential adjustment factor, the sampling frequency can be quickly increased when the temperature suddenly changes and gradually restored to the base value when the temperature approaches stability. Through the temperature change trend term, the acceleration degree of temperature change is additionally considered. If the change speed of the temperature fluctuation anomaly coefficient is fast, the sampling frequency is further increased to make the temperature control system more forward-looking.

[0054] While dynamically adjusting the sampling frequency, further optimize the temperature control response logic. Through the "elastic temperature control window" mechanism, adaptively adjust the temperature control trigger threshold to avoid the hysteresis or overreaction of the temperature control system caused by a fixed threshold. When the temperature fluctuates violently, actively reduce the threshold to make the temperature control system respond to temperature changes more quickly; when the temperature tends to be stable, automatically relax the threshold to reduce unnecessary adjustments, optimize energy consumption and equipment life. The adjustment formula is as follows: , where is the adjusted temperature control trigger threshold, is the default base temperature control threshold, is the response threshold shrinkage coefficient, which controls the sensitivity of the temperature control system to drastic temperature changes, is the bidirectional non - linear control term, using the hyperbolic tangent function for smooth convergence. When holds, will significantly shrink, making the temperature control system respond more quickly; when holds, is only slightly adjusted to avoid unnecessary over - regulation, is the time decay term, is the time decay intensity factor, is the time scale adjustment parameter, which determines the speed of threshold recovery, is the time step. When time increases, gradually decreases, meaning that the system will relax the temperature control threshold over time to avoid frequent adjustments.

[0055] By adopting function for bidirectional adaptive adjustment, when the temperature fluctuates violently, the temperature control window is automatically tightened, while when the temperature is stable, it is gradually relaxed to avoid unnecessary adjustments. The time decay term is adopted to ensure that the threshold is not frequently adjusted due to short - term fluctuations, but slowly recovers after the temperature stabilizes, reducing the ineffective switching operations of the control system and lowering energy consumption.

[0056] By dynamically adjusting the temperature sampling frequency and adaptively adjusting the temperature control response threshold, this step can ensure that the temperature control system of the storage room has a higher response speed and refined monitoring ability when the temperature fluctuates violently, while reducing unnecessary control actions when the temperature tends to be stable, so as to achieve a balance between precise control and energy - saving optimization. The core of this mechanism lies in constructing an intelligent and adaptive temperature control strategy, enabling the system to operate in the optimal way under different temperature change states, and ensuring that the musical instrument storage environment is always in a safe and stable state.

[0057] When the deep - learning model evaluates that the temperature in the storage room enters the rapid - change stage, the temperature transmitter controller will immediately increase the sampling frequency, for example, from the original once every 3 minutes to sampling every 5 seconds, in order to capture the tiny trend of temperature change and provide higher - precision data support. At the same time, the system will shrink the temperature control response threshold, that is, trigger the control strategy (such as starting the refrigeration, heating or air - circulation equipment) immediately when the temperature deviates slightly, so as to quickly stabilize the temperature and prevent sudden temperature differences from damaging the musical instrument structure. For example, if the temperature control system allows a fluctuation range of ±1°C under the original setting, but when the temperature fluctuates violently, the system will actively adjust the threshold to ±0.2°C to ensure higher temperature control accuracy.

[0058] Conversely, when the temperature change amplitude tends to be stable, the system will reduce the sampling frequency (e.g., from sampling every 5 seconds back to once every 3 minutes) and relax the temperature control response threshold. For example, the allowable temperature fluctuation range will be restored to ±1°C to reduce the frequent startup of control devices, lower energy consumption and equipment wear. This can prevent the frequent switching of temperature control devices due to the system being too sensitive, avoid unnecessary energy consumption, and extend the equipment life.

[0059] This "elastic temperature control window" mechanism enables the temperature control system to dynamically adjust the sampling frequency and control accuracy according to the actual environmental requirements, providing the most accurate control when high-precision regulation is needed, and maintaining reasonable energy consumption management when the temperature is relatively stable, thus achieving efficient, intelligent, and energy-saving temperature management.

[0060] Experimental data examples and analysis To verify the effectiveness of the above intelligent temperature control strategy, we conducted experiments in the environment of a musical instrument storage room. The set target temperature range of the storage room is , the basic temperature sampling time (i.e., sampling once every 3 minutes), the initial temperature control trigger threshold , and the temperature fluctuation anomaly coefficient is calculated through a pre-trained deep learning model, and compared and analyzed with the preset reference threshold of the temperature fluctuation anomaly coefficient.

[0061] During the experiment, the environmental temperature was stable within the first 30 minutes, and the system evaluation remained between 0.4 - 0.5, lower than . The system maintained the basic sampling time (i.e., sampling once every 3 minutes), the temperature control threshold remained at , without over-regulation, and the energy consumption was stable.

[0062] Subsequently, we simulated that the storage room door was frequently opened and closed, and an external heat source was added, resulting in the temperature rising from 20.0°C to 21.2°C within 5 minutes. At the same time suddenly rose to 1.1, higher than . The system entered the rapid change state . The sampling time was adaptively adjusted to (i.e., sampling once every 5 seconds) to monitor the temperature change at a higher frequency.

[0063] The temperature control threshold was reduced to . The system became more sensitive, quickly triggered the regulation, and started the cooling system After 8 minutes of regulation, the temperature dropped back to 20.3°C, dropped to 0.5. The system detected that the temperature fluctuation tended to be stable and automatically restored the basic sampling time (Sampling once every 3 minutes), the temperature control threshold is relaxed to to prevent frequent start and stop.

[0064] The results of this experiment show that the intelligent temperature control strategy can effectively sense sudden temperature changes and achieve precise temperature control by dynamically adjusting the sampling time (from 3 minutes to 5 seconds) and the temperature control threshold, reducing energy consumption and improving system stability when the temperature is stable.

[0065] By introducing an intelligent temperature control strategy based on PID control, combining deep learning, adaptive sampling frequency adjustment and elastic temperature control window, the present invention effectively solves the problem of response lag of traditional fixed detection cycle temperature control systems and realizes precise monitoring and dynamic adjustment of the temperature in the musical instrument storage room. The beneficial effects of the present invention are as follows: through real-time collection, preprocessing and feature extraction of environmental data, it can accurately identify abnormal fluctuations in the temperature of the storage room, and use deep learning to intelligently evaluate the temperature change trend to ensure that the temperature control system can dynamically shorten the sampling cycle and quickly respond and adjust when sudden temperature fluctuations occur, avoiding irreversible damages such as thermal expansion and contraction, cracking, paint layer damage, and string breakage of wooden musical instruments caused by temperature change lag. In addition, the elastic temperature control window mechanism proposed by the present invention actively reduces the control threshold when the temperature changes violently to improve the temperature control accuracy, automatically relaxes the threshold after the temperature stabilizes, reduces unnecessary control actions, avoids frequent start and stop of the temperature control system, reduces energy consumption and equipment loss, and thus improves the energy saving of the system and the service life of the temperature control equipment while ensuring the storage safety of musical instruments. The present invention has wide application value in the fields of high-end musical instrument storage, constant temperature protection of museum cultural relics, precise laboratory environment control, etc., and can effectively improve the intelligent level of the temperature control system and ensure the long-term stability and reliability of the temperature environment.

[0066] The above formulas are all dimensionless and take their numerical values for calculation. The formulas are obtained by collecting a large amount of data for software simulation to get a formula closest to the real situation. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0067] Only some exemplary embodiments of the present invention have been described by way of illustration. 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.

[0068] It should be noted that in this document, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprising", "including" or any other variation thereof are intended to cover non-exclusive inclusion, such that a process, method, article or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, article or device comprising the element.

[0069] It should be understood that in various embodiments of the present application, the magnitudes of the sequence numbers of the above processes do not imply the order of execution, and the order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0070] Those of ordinary skill in the art can realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods for each specific application to implement the described functions, but such implementation should not be considered to exceed the scope of the present application.

[0071] 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 foregoing method embodiments, and will not be elaborated herein.

[0072] 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 to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0073] In addition, in various embodiments of the present application, the functional units can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit.

[0074] As described above, it is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present application can easily think of changes or substitutions, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims described above.

[0075] Only some exemplary embodiments of the present invention have been described above by way of illustration. Undoubtedly, for those of ordinary skill in the art, the described embodiments can be modified in various different ways without departing from the spirit and scope of the present invention. Therefore, the above drawings and description are illustrative in nature and should not be construed as limiting the protection scope of the claims of the present invention.

Claims

1. A temperature transmitter controller based on PID control, characterized in that: It includes environmental data acquisition module, environmental data storage and preprocessing module, key feature extraction and fluctuation analysis module, deep learning intelligent evaluation module and adaptive dynamic temperature control module: Environmental data acquisition module, the temperature transmitter controller detects the temperature of the musical instrument storage room according to the established detection cycle, obtains real-time temperature data, lays the foundation for subsequent data analysis and control, and ensures that the musical instrument storage room is stably maintained in the target temperature range under normal circumstances; The environmental data storage and preprocessing module stores all acquired environmental data in chronological order and forms a data set, and preprocesses the environmental data in the data set to ensure the reliability and consistency of the data used in subsequent model analysis; The key feature extraction and fluctuation analysis module, after completing data preprocessing, extracts key features reflecting the rapid change trend of storage room temperature from the preprocessed environmental data set, and analyzes the extracted key features under the detection window to quantify the current ambient temperature fluctuation amplitude; The deep learning intelligent evaluation module inputs the analyzed key features into the pre-trained deep learning model to intelligently evaluate the current temperature change status of the storage room; The adaptive dynamic temperature control module captures the temperature change trend in real time by dynamically adjusting the temperature sampling frequency when the deep learning model evaluation results show that the temperature in the storage room is changing rapidly. At the same time, it adaptively adjusts the response threshold based on the temperature fluctuation amplitude to create a flexible temperature control window. It actively reduces the threshold when the fluctuation is severe and quickly triggers precise adjustment. It automatically relaxes the threshold after the temperature tends to stabilize to avoid energy waste and equipment loss caused by repeated actions.

2. A temperature transmitter controller based on PID control according to claim 1, characterized in that: The specific steps to store all acquired environmental data in chronological order and form a data set are as follows: First, after the temperature transmitter controller obtains the environmental data, all the data are first stored in chronological order to form a structured data set to ensure the integrity and traceability of the data; Next, data preprocessing is performed on the environmental data in the data set, specifically including the following steps:

1. Data cleaning: Identify and remove outliers and missing values, and use interpolation methods to fill in data gaps to prevent model misjudgment; 2. Denoising and smoothing: Remove noise through methods such as sliding mean filtering or Kalman filtering to reduce short-term jitter in temperature data and improve data stability; 3. Unit normalization and standardization: ensure that data from different sources have the same scale to facilitate subsequent analysis and modeling; 4. Time series alignment: For multi-sensor data, synchronize the data according to a unified time step to ensure that the data set remains consistent in the time dimension.

3. A temperature transmitter controller based on PID control according to claim 1, characterized in that: The key features reflecting the rapid change trend of the storage room temperature are extracted from the preprocessed environmental data set. The extracted features include the influence of the opening and closing state of the storage room door on the temperature fluctuation and the abnormal situation of the heat release rate of the objects inside the storage room. The influence of the opening and closing state of the storage room door on the temperature fluctuation and the abnormal situation of the heat release rate of the objects inside the storage room are analyzed under the detection window, and the gated disturbance sensitive reference value and the environmental heat capacity release abnormal reference value are generated respectively. The current ambient temperature fluctuation amplitude is quantified by the gated disturbance sensitive reference value and the environmental heat capacity release abnormal reference value.

4. A temperature transmitter controller based on PID control according to claim 3, characterized in that: The specific steps for analyzing the influence of the open and close state of the storage room door on the temperature fluctuation under the detection window to generate the gated disturbance sensitive reference value are as follows: First, the switch state changes of the storage room door are analyzed to calculate the impact of the door switch disturbance on the temperature. Combined with the door switch frequency, door opening duration, door opening angle, and indoor and outdoor temperature difference factors, the door control disturbance influence factor is defined. The calculation expression is as follows: , where is the gating perturbation factor, It is the number of times the door in the detection window is opened and closed, indicating the frequency of the door opening and closing. is the total time the door in the detection window remains open, is the door opening angle, is the indoor temperature, is the outdoor temperature, , as well as These are the weight parameters that affect the door switch. The influence of control switching times on gate disturbance, Control the effect of gate opening time on gate disturbance, Control the effect of temperature difference on gated perturbations, , as well as are nonlinear exponential adjustment parameters, Control door opening and closing times The nonlinear growth of Control door opening time The impact of disturbances, Controlling temperature difference The degree of magnification, yes Function steepness adjustment parameter, is the natural base; In obtaining the gated perturbation influence factor After that, the direct impact on the temperature change of the storage chamber is further calculated to generate the gated disturbance sensitive reference value. The generation formula is as follows: , where is the gated disturbance sensitive reference value, is the second-order derivative of the temperature field, is the convective heat transfer rate, is the specific heat capacity of air, is the volume of air in the storage chamber, is the weight factor, and They are adjustment parameters, which respectively control the overall weight of the temperature gradient effect and the convective heat transfer effect. is the power parameter, is the scaling factor, is the adjustment factor.

5. The temperature transmitter controller based on PID control according to claim 3, characterized in that: The specific steps for analyzing the abnormal heat release rate of objects inside the storage room to generate the abnormal reference value of environmental heat capacity release are as follows: First, calculate the offset of the instantaneous heat release rate of the object inside the storage room. The walls, floors, storage cabinets and musical instruments in the storage room all have heat capacity effects. Under normal conditions, the heat release rate of the object will follow the law of heat exchange. The heat release rate of the object is calculated by Fourier's law of heat conduction combined with air convection heat transfer. The calculation expression is as follows: , where is the instantaneous heat release rate of the object, is the thermal conductivity of the object, is the surface area of ​​the object, is the temperature gradient between the surface of the object and the air. is the convective heat transfer coefficient, It is the effective contact area between the object and the air for convective heat transfer. is the nonlinear index of convective heat transfer; Under normal circumstances, the heat release of the storage room should be balanced. Even if the temperature changes slightly, the heat capacity effect of the object will buffer the temperature fluctuation. However, when the heat release rate exceeds its normal physical constraint range, it indicates that the temperature change is abnormal. The non-equilibrium is described by the following formula. The calculation expression is as follows: , where is the heat release non-equilibrium index, It is the heat release rate measured in real time by the sensor. It is the theoretical heat release rate calculated based on the normal heat exchange model of the environment. is the weight factor, is the regularization parameter, is the normalization coefficient, is the damping index; Based on the instantaneous heat release rate of the object and heat release non-equilibrium index , generate the reference value of the abnormal release of environmental heat capacity, which is used to quantify the intensity of the abnormal release of environmental heat capacity. The generation formula is as follows: , where is the abnormal reference value of ambient heat capacity release, is the normalized adjustment coefficient, is the scaling factor, is the short-term change impact coefficient, is within the detection window, The actual heat release rate at a time point is is the heat release rate at the previous time point within the detection window, is the number of time points in the detection window, is the rate of change weight.

6. A temperature transmitter controller based on PID control according to claim 3, characterized in that: The analyzed gated disturbance sensitive reference value and ambient heat capacity release abnormal reference value are input into the pre-trained deep learning model, and the temperature fluctuation abnormality coefficient is generated by the deep learning model. The temperature fluctuation abnormality coefficient is used to intelligently evaluate the current temperature change state of the storage room.

7. A temperature transmitter controller based on PID control according to claim 6, characterized in that: The temperature fluctuation anomaly coefficient generated by the intelligent evaluation of the current temperature change state of the storage room by the pre-trained deep learning model is compared and analyzed with the pre-set temperature fluctuation anomaly coefficient reference threshold, and the current temperature change of the storage room is divided. The division steps are as follows: If the temperature fluctuation anomaly coefficient is greater than the preset temperature fluctuation anomaly coefficient reference threshold, the current temperature of the storage chamber is classified as a rapid change state; if the temperature fluctuation anomaly coefficient is less than or equal to the preset temperature fluctuation anomaly coefficient reference threshold, the current temperature of the storage chamber is classified as a stable change state.

8. The temperature transmitter controller based on PID control according to claim 7, characterized in that: When the deep learning model evaluation results show that the storage room temperature is changing rapidly, the temperature sampling frequency is dynamically adjusted, and the response threshold is adaptively adjusted based on the temperature fluctuation amplitude. The specific steps are as follows: When the deep learning model evaluation results show that the storage room temperature is changing rapidly, an adaptive sampling strategy is adopted to adjust the temperature sampling frequency in real time to enhance the responsiveness of the temperature control system. The calculation expression is as follows: , where is the adjusted temperature sampling frequency, is the default base sampling frequency, is the sampling frequency exponential adjustment coefficient, which controls the growth rate of the sampling frequency. is the index adjustment factor, is the natural base, is the temperature fluctuation anomaly coefficient, is the reference threshold of the temperature fluctuation anomaly coefficient, is a very small number, to prevent the denominator from being zero, is the temperature trend term, is the smoothing factor; While dynamically adjusting the sampling frequency, the temperature control response logic is further optimized. Through the "elastic temperature control window" mechanism, the temperature control trigger threshold is adaptively adjusted. The adjustment formula is as follows: , where is the adjusted temperature control trigger threshold, Is the default basic temperature control threshold, is the response threshold shrinkage coefficient, is a bidirectional nonlinear control term using the hyperbolic tangent function To smooth convergence, is the time decay term, is the time decay intensity factor, is the time scale adjustment parameter, is the time step.

Images