Temperature control equipment state intelligent monitoring method and system

Abstract

The invention relates to the technical field of temperature controller data monitoring, in particular to an intelligent monitoring method and system for the state of temperature control equipment. The method comprises the following steps: firstly, collecting current monitoring data, environment sensing data and historical data of the temperature control equipment; processing current display monitoring data, environment sensing data and historical data in the current monitoring data by using an environment influence weight prediction model to obtain a current environment influence weight; obtaining a display state monitoring value according to the current environment influence weight and the current display monitoring data; according to a threshold judgment result of the display state monitoring value, evaluating current control monitoring data in the current monitoring data by using the control monitoring standard value to obtain a control state monitoring value; and inputting the current position information and the current state monitoring information into a temperature control equipment position prediction model according to a threshold judgment result of the control state monitoring value, and optimizing by using a particle swarm algorithm to obtain updated position information.

Description

Technical Field

[0001] The present invention relates to the technical field of temperature controller data monitoring, and in particular to a method and system for intelligently monitoring the status of a temperature control device. Background Art

[0002] Smart thermostats integrate measurement, display, control, alarm, and recording functions, and are equipped with WiFi, OT communication protocols, multiple communication interfaces and other functions. Smart thermostats that incorporate AI and voice can achieve accurate temperature measurement and precise on-site and remote control of the temperature and working status of home appliances via mobile phones. The complex design and functions also bring huge challenges to the monitoring of the status of temperature control equipment.

[0003] At present, the traditional temperature control equipment status monitoring method usually uses the collected current temperature monitoring data to verify and proofread the temperature control equipment status, without combining historical environmental monitoring data to obtain the impact of environmental changes on the temperature control equipment status monitoring; on the other hand, the traditional monitoring method cannot adjust the position of the temperature control equipment according to the current status data of the equipment, which will reduce the accuracy and reliability of the intelligent monitoring of the temperature control equipment status.

[0004] To this end, a method and system for intelligent monitoring of temperature control equipment status are proposed. Summary of the invention

[0005] The purpose of the present invention is to provide a method and system for intelligent monitoring of the state of a temperature control device. First, the current monitoring data, environmental sensor data and historical data of the temperature control device are collected; the current display monitoring data, environmental sensor data and historical data in the current monitoring data are processed using an environmental impact weight prediction model to obtain the current environmental impact weight; the display state monitoring value is obtained according to the current environmental impact weight and the current display monitoring data; according to the threshold judgment result of the display state monitoring value, the current control monitoring data in the current monitoring data is evaluated using the control monitoring standard value to obtain the control state monitoring value; according to the threshold judgment result of the control state monitoring value, the current position information and the current state monitoring information are input into the temperature control device position prediction model and optimized using a particle swarm algorithm to obtain updated position information.

[0006] To achieve the above object, the present invention provides the following technical solutions: A method for intelligently monitoring the status of a temperature control device, comprising: Collect current monitoring data, environmental sensor data, historical display monitoring data and historical environmental sensor data of temperature control equipment; Using the historical display monitoring data and the historical environmental sensor data to train an environmental impact weight prediction model to obtain historical environmental impact weights; Inputting the current display monitoring data, the environmental sensor data and the historical environmental impact weight in the current monitoring data into the pre-trained environmental impact weight prediction model to obtain the current environmental impact weight; weighting the current display monitoring data using the current environmental impact weight to obtain a display state monitoring value; Compare the display state monitoring value with a threshold value, if it is lower than the display threshold value, set the display state monitoring value to 0 and output display abnormality information; otherwise, evaluate the current control monitoring data in the current monitoring data using the control monitoring standard value to obtain the control state monitoring value; The control state monitoring value is compared with a threshold. If it is lower than the control threshold, the control state monitoring value is set to 0 and the control abnormality information is output; otherwise, the current position information and the current state monitoring information are input into the temperature control equipment position prediction model and optimized using the particle swarm algorithm to obtain updated position information.

[0007] Furthermore, the current monitoring data includes: current display monitoring data and current control monitoring data; the environmental sensor data includes: environmental light sensor data and environmental temperature sensor data; the historical environmental sensor data includes: historical environmental light sensor data and historical environmental temperature sensor data.

[0008] Furthermore, the current display monitoring data, the environmental sensor data and the historical environmental impact weight in the current monitoring data are input into the pre-trained environmental impact weight prediction model to obtain the current environmental impact weight; and the current display monitoring data is weighted by using the current environmental impact weight to obtain the display state monitoring value. The specific implementation process includes: Input the current display monitoring data, environmental sensor data and historical environmental impact weights into the pre-trained environmental impact weight prediction model, optimize and update the parameters, and obtain the current environmental impact weight; The current environment impact weights include: a weight affecting temperature display, a weight affecting humidity display, and a weight affecting power display; Obtaining current temperature display data, current humidity display data and current power display data from the current display monitoring data; Calculate the difference between the current temperature display data, the current humidity display data and the current power display data and the actual temperature data, the actual humidity data and the actual power data, respectively, to obtain a current temperature display deviation value, a current humidity display deviation value and a current power display deviation value; The current temperature display deviation value, the current humidity display deviation value, and the current power display deviation value are evaluated using the current environmental impact weight to obtain a display status monitoring value.

[0009] Furthermore, the specific implementation process of evaluating the current control monitoring data in the current monitoring data by using the control monitoring standard value to obtain the control state monitoring value includes: Obtain current control monitoring data and control monitoring standard values; Wherein, the current control monitoring data includes: current control mode data, current control abnormality data, current control delay data and current control temperature data; Obtaining a control mode coefficient and a control abnormality coefficient according to the current control mode data and the current control abnormality data; The control mode coefficient, the control abnormality coefficient, the current control delay data and the current control temperature data are evaluated to obtain a control state monitoring value.

[0010] Furthermore, the current position information and the current state monitoring information are input into the temperature control equipment position prediction model and optimized using the particle swarm algorithm to obtain the updated position information. The specific implementation process includes: Obtain historical location information, historical status monitoring information, current location information, and current status monitoring information; Wherein, the historical status monitoring information includes historical display status monitoring values ​​and historical control status monitoring values; the current status monitoring information includes current display status monitoring values ​​and current control status monitoring values; Using the historical location information and the historical status monitoring information to train a temperature control device location prediction model to obtain a pre-trained device location prediction model; Inputting the current position information and the current state monitoring information into the pre-trained device position prediction model to obtain predicted position information; The predicted position information is set as the initialization particle position, with maximizing the display state monitoring value and maximizing the control state monitoring value as the optimization goal, and the particle swarm algorithm is used for iteration to obtain the updated position information.

[0011] Furthermore, the specific implementation process of iterating using the particle swarm algorithm to obtain the updated position information includes: The optimization objectives of the particle swarm algorithm are set to maximize the display state monitoring value and maximize the control state monitoring value; A group of particles is randomly generated, and an initial position and an initial velocity are set for each particle to form an initial particle group; and a global optimal position and an optimal fitness are set at the same time; wherein the initial position is set to the predicted position information output by the pre-trained device position prediction model; Using a particle swarm optimization algorithm to update the speed and position of the particle according to the current position, current speed, historical optimal position and the global optimal position of the particle; After each position update, the fitness value of the particle is calculated, and the local optimal position and the global optimal position of the particle are updated according to the fitness value; then, it is determined whether the current number of iterations exceeds the preset maximum number of iterations. If it exceeds, the optimization process is terminated and the adjustment variable value corresponding to the global optimal position is output, that is, the position information is updated.

[0012] An intelligent monitoring system for the state of a temperature control device, comprising: a system control module, a data acquisition module, a display state monitoring module, a control state monitoring module, a temperature control device position prediction module and an output module; Wherein, the system control module is used to control the start, pause and stop of the system; The data acquisition module is used to obtain current monitoring data, environmental sensor data, historical display monitoring data and historical environmental sensor data of the temperature control device; The display status monitoring module is used to weight the current display monitoring data using the current environmental impact weight output by the environmental impact weight prediction model to obtain a display status monitoring value and perform display threshold comparison; The control state monitoring module is used to evaluate the current control monitoring data using the control monitoring standard value, obtain the control state monitoring value, and perform control threshold comparison; The temperature control device position prediction module is used to process data using the temperature control device position prediction model and the particle swarm algorithm to obtain updated position information; The output module is used to output the abnormality information and the update position information.

[0013] Furthermore, the display status monitoring module is used to weight the current display monitoring data using the current environmental impact weight output by the environmental impact weight prediction model to obtain the display status monitoring value. The specific implementation process includes: The environmental impact weight prediction model is trained using historical display monitoring data and historical environmental sensor data to obtain historical environmental impact weights; Inputting the current display monitoring data, environmental sensor data and the historical environmental impact weights into the environmental impact weight prediction model, optimizing and updating parameters, and obtaining the current environmental impact weights; Calculate the difference between the current temperature display data, the current humidity display data and the current power display data and the actual temperature data, the actual humidity data and the actual power data, respectively, to obtain the current temperature display deviation value, the current humidity display deviation value and the current power display deviation value; The current temperature display deviation value, the current humidity display deviation value, and the current power display deviation value are evaluated using the current environmental impact weight to obtain a display status monitoring value.

[0014] Furthermore, the control state monitoring module is used to evaluate the current control monitoring data using the control monitoring standard value, and the specific implementation process of obtaining the control state monitoring value includes: Obtain current control monitoring data and control monitoring standard values; Wherein, the current control monitoring data includes: current control mode data, current control abnormality data, current control delay data and current control temperature data; Obtaining a control mode coefficient and a control abnormality coefficient according to the current control mode data and the current control abnormality data; The control mode coefficient, the control abnormality coefficient, the current control delay data and the current control temperature data are evaluated to obtain a control state monitoring value.

[0015] Furthermore, the temperature control device position prediction module is used to perform data processing using the temperature control device position prediction model and the particle swarm algorithm, and the specific implementation process of obtaining the updated position information includes: Obtain historical location information, historical status monitoring information, current location information, and current status monitoring information; Wherein, the historical status monitoring information includes historical display status monitoring values ​​and historical control status monitoring values; the current status monitoring information includes current display status monitoring values ​​and current control status monitoring values; Using the historical location information and the historical status monitoring information to train a temperature control device location prediction model to obtain a pre-trained device location prediction model; Inputting the current position information and the current state monitoring information into the pre-trained device position prediction model to obtain predicted position information; The predicted position information is set as the initialization particle position, with maximizing the display state monitoring value and maximizing the control state monitoring value as the optimization goal, and the particle swarm algorithm is used for iteration to obtain the updated position information.

[0016] Compared with the prior art, the present invention has the following beneficial effects: 1. The present invention proposes a display status monitoring function for monitoring the display status of a temperature control device; the function first uses historical display monitoring data and historical environmental sensing data to train an environmental impact weight prediction model to obtain historical environmental impact weights; then, the current display monitoring data is weighted using the current environmental impact weight output by the environmental impact weight prediction model to obtain a display status monitoring value; the display status monitoring value can reflect the degree of interference of ambient light and temperature changes on the display status of the temperature control device, thereby effectively improving the accuracy and reliability of intelligent monitoring of the temperature control device status.

[0017] 2. The present invention proposes a control status monitoring function for monitoring the control status of a temperature control device; this function obtains a control mode coefficient and a control abnormality coefficient by collecting current control mode data and current control abnormality data; then, the current control delay data and the current control temperature data are evaluated in combination with the control mode coefficient and the control abnormality coefficient to obtain a control status monitoring value; this function can effectively monitor various dimensions of the temperature control device control according to the control status monitoring value, thereby effectively improving the accuracy and reliability of intelligent monitoring of the temperature control device status.

[0018] 3. The present invention proposes a temperature control device position prediction function for adjusting the position of the temperature control device according to real-time monitoring information; the function uses a pre-trained device position prediction model trained by historical position information and historical status monitoring information to predict the position of the temperature control device to obtain predicted position information; then, the function uses a particle swarm algorithm to iteratively optimize the predicted position information to obtain updated position information; the position information obtained by this function is less affected by environmental interference and can achieve stable control performance, thereby further improving the accuracy and reliability of intelligent monitoring of the temperature control device status. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 A schematic diagram of a flow chart of a method for intelligently monitoring the status of a temperature control device according to the present invention; Figure 2 It is a structural schematic diagram of the environmental impact weight prediction model of the present invention; Figure 3 It is a structural schematic diagram of an intelligent monitoring system for temperature control equipment status of the present invention. DETAILED DESCRIPTION

[0020] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0021] Embodiment 1 Smart thermostats integrate measurement, display, control, alarm, and recording functions, and are equipped with WiFi, OT communication protocols, multiple communication interfaces and other functions. Smart thermostats that incorporate AI and voice can achieve accurate temperature measurement and precise on-site and remote control of the temperature and working status of home appliances via mobile phones. The complex design and functions also bring huge challenges to the monitoring of the status of temperature control equipment.

[0022] In order to improve the user experience of the intelligent thermostat, a certain intelligent thermostat manufacturer introduced a temperature control device status intelligent monitoring method provided by the present invention. The process can be referred to Figure 1 , the specific implementation is as follows: First, collect the current monitoring data, environmental sensor data, historical display monitoring data and historical environmental sensor data of the temperature control equipment; Furthermore, the current monitoring data includes: current display monitoring data and current control monitoring data; the environmental sensor data includes: environmental light sensor data and environmental temperature sensor data; the historical environmental sensor data includes: historical environmental light sensor data and historical environmental temperature sensor data.

[0023] Furthermore, the parameter values ​​of the current display monitoring data and environmental sensing data are shown in Table 1.

[0024] Table 1. Parameter data of current display monitoring data and environmental sensor data

[0025] In this embodiment, historical environmental sensor data is used to train the environmental impact weight prediction model to predict the changing trend of past environmental factors on the display data; current monitoring data and environmental sensor data provide a strong data basis for display status monitoring and control status monitoring.

[0026] Using the historical display monitoring data and the historical environmental sensor data to train an environmental impact weight prediction model to obtain historical environmental impact weights; Inputting the current display monitoring data, the environmental sensor data and the historical environmental impact weight in the current monitoring data into the pre-trained environmental impact weight prediction model to obtain the current environmental impact weight; weighting the current display monitoring data using the current environmental impact weight to obtain a display state monitoring value; Furthermore, the specific implementation process of displaying the status monitoring value includes: Input the current display monitoring data, environmental sensor data and historical environmental impact weights into the pre-trained environmental impact weight prediction model, optimize and update the parameters, and obtain the current environmental impact weight; The current environment impact weights include: a weight affecting temperature display, a weight affecting humidity display, and a weight affecting power display; The structure of the environmental impact weight prediction model in this embodiment can be referred to Figure 2, including: input layer, CNN-LSTM feature extraction layer, feature merging layer, environmental impact weight prediction layer and output layer; the input layer is used to map the current display monitoring data, environmental sensor data and historical environmental impact weights into the feature space for the next step of processing; the CNN-LSTM feature extraction layer is used to extract the temporal features of LSTM and the spatial features of CNN; the feature merging layer is used to merge the temporal features and spatial features into channels; the environmental impact weight prediction layer uses a multilayer perceptron to obtain the weight prediction results; the output layer outputs the current environmental impact weight through a linear activation function.

[0027] Obtaining current temperature display data, current humidity display data and current power display data from the current display monitoring data; Calculate the difference between the current temperature display data, the current humidity display data and the current power display data and the actual temperature data, the actual humidity data and the actual power data, respectively, to obtain a current temperature display deviation value, a current humidity display deviation value and a current power display deviation value; The current temperature display deviation value, the current humidity display deviation value, and the current power display deviation value are evaluated using the current environmental impact weight to obtain a display status monitoring value.

[0028] Furthermore, the calculation formula of the display status monitoring value is: ; Among them, XSJC is the display status monitoring value, which is in the range of [0, 1] and the larger the value, the more normal the temperature control device display; N is the number of times sample data is collected; Display weights for influencing temperature; Display the current temperature data collected for the i-th time; is the actual temperature data; Display weights for influencing humidity; Display the current humidity data collected for the i-th time; is the actual humidity data; Display weights for impact power; The current power display data collected for the i-th time; The actual power data.

[0029] Further, the influence of temperature display weight , Affects humidity display weight and influence power display weight The weight value is obtained from the output of the environmental impact weight prediction model, and is between [0, 1].

[0030] Furthermore, the four sets of current display data collected from the 8th to the 11th time are used to obtain the display status monitoring results of the temperature control device using the calculation formula of the display status monitoring value, as shown in Table 2 below, and the display threshold is set to 0.9.

[0031] Table 2. Temperature control equipment display status monitoring results

[0032] In this embodiment, a display status monitoring function is proposed for monitoring the display status of the temperature control device; the function first uses historical display monitoring data and historical environmental sensor data to train the environmental impact weight prediction model to obtain the historical environmental impact weight; then, the current display monitoring data is weighted using the current environmental impact weight output by the environmental impact weight prediction model to obtain a display status monitoring value; the display status monitoring value can reflect the degree of interference of ambient light and temperature changes on the display status of the temperature control device, thereby effectively improving the accuracy and reliability of intelligent monitoring of the temperature control device status.

[0033] Compare the display state monitoring value with a threshold value, if it is lower than the display threshold value, set the display state monitoring value to 0 and output display abnormality information; otherwise, evaluate the current control monitoring data in the current monitoring data using the control monitoring standard value to obtain the control state monitoring value; Furthermore, the specific implementation process of evaluating the current control monitoring data in the current monitoring data by using the control monitoring standard value to obtain the control state monitoring value includes: Obtain current control monitoring data and control monitoring standard values; The current control monitoring data includes: current control mode data, current control abnormality data, current control delay data and current control temperature data; the current control mode data is represented by indoor temperature data under different control modes, and the current control abnormality data is represented by abnormal deviation value between target temperature and actual temperature; Obtaining a control mode coefficient and a control abnormality coefficient according to the current control mode data and the current control abnormality data; The control mode coefficient, the control abnormality coefficient, the current control delay data and the current control temperature data are evaluated to obtain a control state monitoring value.

[0034] Furthermore, the control mode coefficient and the control abnormality coefficient are expressed as: ;in, is the control mode coefficient, It is the indoor temperature change value when the temperature control device is turned on and off. Set the temperature for the target, To control the abnormal coefficient, is the actual temperature, is the allowable temperature deviation range; the control mode coefficient indicates the influence of the temperature control equipment on the indoor temperature change under different working modes; the control abnormality coefficient indicates the temperature control performance of the temperature control equipment under abnormal working conditions.

[0035] Furthermore, the calculation formula of the control state monitoring value is: ; Among them, KZJC is the control status monitoring value, which is in the range of [0, 1] and the larger the value, the more normal the temperature control equipment control; is the control mode coefficient, is the control abnormality coefficient; KZPG is the control status evaluation value; M is the number of data collection times; To control the delay weight; is the current control delay data collected for the jth time; To control the delay threshold; To control the temperature weight; is the current control temperature data collected for the jth time; To control the temperature threshold.

[0036] In this embodiment, the control delay weight and the control temperature weight are both set to 0.5; the control delay threshold and the control temperature threshold are related to the model and performance of the temperature control device and can be adjusted according to actual conditions.

[0037] Furthermore, the four sets of current control monitoring data collected from the 23rd to 26th times are used to obtain the temperature control equipment control state monitoring results using the calculation formula of the control state monitoring value, as shown in Table 3 below, and the control threshold is set to 0.85.

[0038] Table 3. Temperature control equipment display status monitoring results

[0039] In this embodiment, a control status monitoring function is proposed to monitor the control status of the temperature control device; this function obtains the control mode coefficient and the control abnormality coefficient by collecting the current control mode data and the current control abnormality data; then, the current control delay data and the current control temperature data are evaluated in combination with the control mode coefficient and the control abnormality coefficient to obtain the control status monitoring value; this function can effectively monitor the various dimensions of the temperature control device control according to the control status monitoring value, thereby effectively improving the accuracy and reliability of the intelligent monitoring of the temperature control device status.

[0040] The control state monitoring value is compared with a threshold. If it is lower than the control threshold, the control state monitoring value is set to 0 and the control abnormality information is output; otherwise, the current position information and the current state monitoring information are input into the temperature control equipment position prediction model and optimized using the particle swarm algorithm to obtain updated position information.

[0041] Furthermore, the current position information and the current state monitoring information are input into the temperature control equipment position prediction model and optimized using the particle swarm algorithm to obtain the updated position information. The specific implementation process includes: Obtain historical location information, historical status monitoring information, current location information, and current status monitoring information; Wherein, the historical status monitoring information includes historical display status monitoring values ​​and historical control status monitoring values; the current status monitoring information includes current display status monitoring values ​​and current control status monitoring values; Using the historical location information and the historical status monitoring information to train a temperature control device location prediction model to obtain a pre-trained device location prediction model; Inputting the current position information and the current state monitoring information into the pre-trained device position prediction model to obtain predicted position information; The predicted position information is set as the initial particle position, and the particle swarm algorithm is used to iterate with the maximization of the state monitoring information as the optimization goal to obtain the updated position information.

[0042] In this embodiment, a temperature control device position prediction function is proposed for adjusting the position of the temperature control device according to real-time monitoring information; the function uses a pre-trained device position prediction model trained with historical position information and historical status monitoring information to predict the position of the temperature control device to obtain predicted position information; then, the function uses a particle swarm algorithm to iteratively optimize the predicted position information to obtain updated position information; the position information obtained by this function is less affected by environmental interference and can achieve stable control performance, thereby further improving the accuracy and reliability of intelligent monitoring of the temperature control device status.

[0043] In this embodiment, a method for intelligent monitoring of the state of a temperature control device is proposed. By using the display state monitoring value obtained by using the current environmental impact weight and the current display monitoring data, and the control state monitoring value obtained by evaluating the current control monitoring data, the monitoring time of the device in different states can be effectively shortened, and the accuracy and reliability of intelligent monitoring of the state of the temperature control device can be improved; at the same time, according to the threshold judgment result of the control state monitoring value, the prediction result of the temperature control device position prediction model and the iterative optimization of the particle swarm algorithm are used to obtain updated position information, which can improve the stability of the working state of the temperature control device, thereby improving the user experience.

[0044] Embodiment 2 In this embodiment, a temperature control equipment status intelligent monitoring system is provided, and the system structure is as follows: Figure 3 As shown, the specific implementation is as follows: The system control module is used to control the start, pause and stop of the system; Data acquisition module, used to obtain current monitoring data, environmental sensor data, historical display monitoring data and historical environmental sensor data of temperature control equipment; A display state monitoring module is used to weight the current display monitoring data using the current environmental impact weight output by the environmental impact weight prediction model to obtain a display state monitoring value and perform display threshold comparison; the display state monitoring module includes a display state monitoring unit and a judgment unit; Furthermore, the display status monitoring unit uses the current environmental impact weight output by the environmental impact weight prediction model to weight the current display monitoring data, and the specific implementation process of obtaining the display status monitoring value includes: The environmental impact weight prediction model is trained using historical display monitoring data and historical environmental sensor data to obtain historical environmental impact weights; Inputting the current display monitoring data, environmental sensor data and the historical environmental impact weights into the environmental impact weight prediction model, optimizing and updating parameters, and obtaining the current environmental impact weights; Calculate the difference between the current temperature display data, the current humidity display data and the current power display data and the actual temperature data, the actual humidity data and the actual power data, respectively, to obtain the current temperature display deviation value, the current humidity display deviation value and the current power display deviation value; The current temperature display deviation value, the current humidity display deviation value, and the current power display deviation value are evaluated using the current environmental impact weight to obtain a display status monitoring value.

[0045] Furthermore, the display status monitoring unit obtains the monitoring result of the display status monitoring unit by using the four sets of current display data collected for the 42nd to 45th times and combining with the calculation formula of the display status monitoring value, as shown in Table 4 below.

[0046] Table 4. Monitoring results of display status monitoring unit

[0047] Furthermore, the judgment unit is used to compare the display status monitoring value with the display threshold.

[0048] A control state monitoring module is used to evaluate the current control monitoring data using the control monitoring standard value, obtain the control state monitoring value, and compare the control threshold value; the control state monitoring module includes a control state monitoring unit and a judgment unit; Furthermore, the control state monitoring unit evaluates the current control monitoring data using the control monitoring standard value, and the specific implementation process of obtaining the control state monitoring value includes: Obtain current control monitoring data and control monitoring standard values; Wherein, the current control monitoring data includes: current control mode data, current control abnormality data, current control delay data and current control temperature data; Obtaining a control mode coefficient and a control abnormality coefficient according to the current control mode data and the current control abnormality data; The control mode coefficient, the control abnormality coefficient, the current control delay data and the current control temperature data are evaluated to obtain a control state monitoring value.

[0049] Furthermore, the control state monitoring unit uses the four sets of current control monitoring data collected from the 84th to the 87th time and combines the calculation formula of the control state monitoring value to obtain the monitoring result of the control state monitoring unit, as shown in Table 5 below.

[0050] Table 5. Monitoring results of control status monitoring unit

[0051] Further, the judgment unit is used to compare the control state monitoring value with the control threshold.

[0052] The temperature control equipment position prediction module is used to process data using the temperature control equipment position prediction model and the particle swarm algorithm to obtain updated position information; the temperature control equipment position prediction module includes a temperature control equipment position prediction unit and a position optimization unit; Furthermore, the specific implementation process of the temperature control device position prediction unit obtaining the predicted position information by using the temperature control device position prediction model includes: Obtain historical location information, historical status monitoring information, current location information, and current status monitoring information; Wherein, the historical status monitoring information includes historical display status monitoring values ​​and historical control status monitoring values; the current status monitoring information includes current display status monitoring values ​​and current control status monitoring values; Using the historical location information and the historical status monitoring information to train a temperature control device location prediction model to obtain a pre-trained device location prediction model; The current position information and the current state monitoring information are input into the pre-trained device position prediction model to obtain the predicted position information.

[0053] Furthermore, the location optimization unit uses the particle swarm algorithm to iterate, and the process of obtaining updated location information includes: The optimization objectives of the particle swarm algorithm are set to maximize the display state monitoring value and maximize the control state monitoring value; A group of particles is randomly generated, and an initial position and an initial velocity are assigned to each particle to form an initial particle group; and a global optimal position and an optimal fitness are set at the same time; wherein the initial position is set to the predicted position information output by the pre-trained device position prediction model; Using a particle swarm optimization algorithm to update the speed and position of the particle according to the current position, current speed, historical optimal position and the global optimal position of the particle; After each position update, the fitness value of the particle is calculated, and the local optimal position and the global optimal position of the particle are updated according to the fitness value; then, it is determined whether the current number of iterations exceeds the preset maximum number of iterations. If it exceeds, the optimization process is terminated and the adjustment variable value corresponding to the global optimal position is output, that is, the position information is updated.

[0054] The output module is used to output abnormal information and update location information.

[0055] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for intelligent monitoring of temperature control equipment status, characterized in that: include: Collect current monitoring data, environmental sensor data, historical display monitoring data and historical environmental sensor data of temperature control equipment; Using the historical display monitoring data and the historical environmental sensor data to train an environmental impact weight prediction model to obtain historical environmental impact weights; Inputting the current display monitoring data, the environmental sensor data and the historical environmental impact weight in the current monitoring data into the pre-trained environmental impact weight prediction model to obtain the current environmental impact weight; weighting the current display monitoring data using the current environmental impact weight to obtain a display state monitoring value; Compare the display status monitoring value with a threshold value, and if it is lower than the display threshold value, set the display status monitoring value to 0 and output display abnormality information; otherwise, evaluating the current control monitoring data in the current monitoring data using the control monitoring standard value to obtain a control state monitoring value; The control state monitoring value is compared with a threshold. If it is lower than the control threshold, the control state monitoring value is set to 0 and the control abnormality information is output; otherwise, the current position information and the current state monitoring information are input into the temperature control equipment position prediction model and optimized using the particle swarm algorithm to obtain updated position information.

2. The method for intelligent monitoring of temperature control equipment status according to claim 1, characterized in that: The current monitoring data includes: current display monitoring data and current control monitoring data; the environmental sensor data includes: environmental light sensor data and environmental temperature sensor data; the historical environmental sensor data includes: historical environmental light sensor data and historical environmental temperature sensor data.

3. The method for intelligently monitoring the status of a temperature control device according to claim 1, characterized in that: Inputting the currently displayed monitoring data, the environmental sensing data and the historical environmental impact weight in the current monitoring data into the pre-trained environmental impact weight prediction model to obtain the current environmental impact weight; The specific implementation process of weighting the current display monitoring data by using the current environmental impact weight to obtain the display state monitoring value includes: Input the current display monitoring data, environmental sensor data and historical environmental impact weights into the pre-trained environmental impact weight prediction model, optimize and update the parameters, and obtain the current environmental impact weight; The current environment impact weights include: a weight affecting temperature display, a weight affecting humidity display, and a weight affecting power display; Obtaining current temperature display data, current humidity display data and current power display data from the current display monitoring data; Calculate the difference between the current temperature display data, the current humidity display data and the current power display data and the actual temperature data, the actual humidity data and the actual power data, respectively, to obtain a current temperature display deviation value, a current humidity display deviation value and a current power display deviation value; The current temperature display deviation value, the current humidity display deviation value, and the current power display deviation value are evaluated using the current environmental impact weight to obtain a display status monitoring value.

4. The method for intelligently monitoring the status of a temperature control device according to claim 1, characterized in that: The specific implementation process of evaluating the current control monitoring data in the current monitoring data by using the control monitoring standard value to obtain the control state monitoring value includes: Obtain current control monitoring data and control monitoring standard values; Wherein, the current control monitoring data includes: current control mode data, current control abnormality data, current control delay data and current control temperature data; Obtaining a control mode coefficient and a control abnormality coefficient according to the current control mode data and the current control abnormality data; The control mode coefficient, the control abnormality coefficient, the current control delay data and the current control temperature data are evaluated to obtain a control state monitoring value.

5. The method for intelligently monitoring the status of a temperature control device according to claim 1, characterized in that: The current position information and current status monitoring information are input into the temperature control equipment position prediction model and optimized using the particle swarm algorithm to obtain the updated position information. The specific implementation process includes: Obtain historical location information, historical status monitoring information, current location information, and current status monitoring information; Wherein, the historical status monitoring information includes historical display status monitoring values ​​and historical control status monitoring values; the current status monitoring information includes current display status monitoring values ​​and current control status monitoring values; Using the historical location information and the historical status monitoring information to train a temperature control device location prediction model to obtain a pre-trained device location prediction model; Inputting the current position information and the current state monitoring information into the pre-trained device position prediction model to obtain predicted position information; The predicted position information is set as the initialization particle position, with maximizing the display state monitoring value and maximizing the control state monitoring value as the optimization goal, and the particle swarm algorithm is used for iteration to obtain the updated position information.

6. A method for intelligently monitoring the status of a temperature control device according to claim 5, characterized in that: The specific implementation process of iterating using the particle swarm algorithm to obtain updated position information includes: The optimization objectives of the particle swarm algorithm are set to maximize the display state monitoring value and maximize the control state monitoring value; A group of particles is randomly generated, and an initial position and an initial velocity are set for each particle to form an initial particle group; and a global optimal position and an optimal fitness are set at the same time; wherein the initial position is set to the predicted position information output by the pre-trained device position prediction model; Using a particle swarm optimization algorithm to update the speed and position of the particle according to the current position, current speed, historical optimal position and the global optimal position of the particle; After each position update, the fitness value of the particle is calculated, and the local optimal position and the global optimal position of the particle are updated according to the fitness value; then, it is determined whether the current number of iterations exceeds the preset maximum number of iterations. If it exceeds, the optimization process is terminated and the adjustment variable value corresponding to the global optimal position is output, that is, the position information is updated.

7. An intelligent monitoring system for temperature control equipment status, characterized in that: include: System control module, data acquisition module, display status monitoring module, control status monitoring module, temperature control equipment position prediction module and output module; Wherein, the system control module is used to control the start, pause and stop of the system; The data acquisition module is used to obtain current monitoring data, environmental sensor data, historical display monitoring data and historical environmental sensor data of the temperature control device; The display status monitoring module is used to weight the current display monitoring data using the current environmental impact weight output by the environmental impact weight prediction model to obtain a display status monitoring value and perform display threshold comparison; The control state monitoring module is used to evaluate the current control monitoring data using the control monitoring standard value, obtain the control state monitoring value, and perform control threshold comparison; The temperature control device position prediction module is used to process data using the temperature control device position prediction model and the particle swarm algorithm to obtain updated position information; The output module is used to output the abnormality information and the update position information.

8. The intelligent monitoring system for temperature control equipment status according to claim 7, characterized in that: The display status monitoring module is used to weight the current display monitoring data using the current environmental impact weight output by the environmental impact weight prediction model to obtain the display status monitoring value. The specific implementation process includes: The environmental impact weight prediction model is trained using historical display monitoring data and historical environmental sensor data to obtain historical environmental impact weights; Inputting the current display monitoring data, environmental sensor data and the historical environmental impact weights into the environmental impact weight prediction model, optimizing and updating parameters, and obtaining the current environmental impact weights; Calculate the difference between the current temperature display data, the current humidity display data and the current power display data and the actual temperature data, the actual humidity data and the actual power data, respectively, to obtain the current temperature display deviation value, the current humidity display deviation value and the current power display deviation value; The current temperature display deviation value, the current humidity display deviation value, and the current power display deviation value are evaluated using the current environmental impact weight to obtain a display status monitoring value.

9. The intelligent monitoring system for temperature control equipment status according to claim 7, characterized in that: The control state monitoring module is used to evaluate the current control monitoring data using the control monitoring standard value, and the specific implementation process of obtaining the control state monitoring value includes: Obtain current control monitoring data and control monitoring standard values; Wherein, the current control monitoring data includes: current control mode data, current control abnormality data, current control delay data and current control temperature data; Obtaining a control mode coefficient and a control abnormality coefficient according to the current control mode data and the current control abnormality data; The control mode coefficient, the control abnormality coefficient, the current control delay data and the current control temperature data are evaluated to obtain a control state monitoring value.

10. The intelligent monitoring system for temperature control equipment status according to claim 7, characterized in that: The temperature control device position prediction module is used to process data using the temperature control device position prediction model and the particle swarm algorithm, and the specific implementation process of obtaining updated position information includes: Obtain historical location information, historical status monitoring information, current location information, and current status monitoring information; Wherein, the historical status monitoring information includes historical display status monitoring values ​​and historical control status monitoring values; the current status monitoring information includes current display status monitoring values ​​and current control status monitoring values; Using the historical location information and the historical status monitoring information to train a temperature control device location prediction model to obtain a pre-trained device location prediction model; Inputting the current position information and the current state monitoring information into the pre-trained device position prediction model to obtain predicted position information; The predicted position information is set as the initialization particle position, with maximizing the display state monitoring value and maximizing the control state monitoring value as the optimization goal, and the particle swarm algorithm is used for iteration to obtain the updated position information.

Images