CN116755497A - Monitoring control system for cabinet and control method thereof - Google Patents
Monitoring control system for cabinet and control method thereof Download PDFInfo
- Publication number
- CN116755497A CN116755497A CN202311047503.XA CN202311047503A CN116755497A CN 116755497 A CN116755497 A CN 116755497A CN 202311047503 A CN202311047503 A CN 202311047503A CN 116755497 A CN116755497 A CN 116755497A
- Authority
- CN
- China
- Prior art keywords
- humidity
- temperature
- data
- error
- cabinet
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 37
- 238000012544 monitoring process Methods 0.000 title claims abstract description 32
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 54
- 238000012545 processing Methods 0.000 claims abstract description 14
- 230000033228 biological regulation Effects 0.000 claims abstract description 9
- 238000012549 training Methods 0.000 claims description 58
- 230000006870 function Effects 0.000 claims description 53
- 230000008859 change Effects 0.000 claims description 27
- 239000000779 smoke Substances 0.000 claims description 26
- 238000012360 testing method Methods 0.000 claims description 20
- 238000004891 communication Methods 0.000 claims description 17
- 230000007613 environmental effect Effects 0.000 claims description 12
- 238000011478 gradient descent method Methods 0.000 claims description 7
- 238000013135 deep learning Methods 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 6
- 230000002159 abnormal effect Effects 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000010276 construction Methods 0.000 claims description 3
- 230000005236 sound signal Effects 0.000 claims description 3
- 238000012423 maintenance Methods 0.000 description 25
- 230000001276 controlling effect Effects 0.000 description 11
- 238000005457 optimization Methods 0.000 description 10
- 238000010586 diagram Methods 0.000 description 9
- 238000007726 management method Methods 0.000 description 8
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000010801 machine learning Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 239000000243 solution Substances 0.000 description 3
- 238000013459 approach Methods 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 230000001186 cumulative effect Effects 0.000 description 2
- 230000007423 decrease Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 239000000428 dust Substances 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000013468 resource allocation Methods 0.000 description 2
- 238000012300 Sequence Analysis Methods 0.000 description 1
- 230000005856 abnormality Effects 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 239000000956 alloy Substances 0.000 description 1
- 229910045601 alloy Inorganic materials 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000003749 cleanliness Effects 0.000 description 1
- 239000010960 cold rolled steel Substances 0.000 description 1
- 239000012141 concentrate Substances 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 230000000593 degrading effect Effects 0.000 description 1
- 238000009795 derivation Methods 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000002347 injection Methods 0.000 description 1
- 239000007924 injection Substances 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 238000011056 performance test Methods 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000013112 stability test Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D27/00—Simultaneous control of variables covered by two or more of main groups G05D1/00 - G05D25/00
- G05D27/02—Simultaneous control of variables covered by two or more of main groups G05D1/00 - G05D25/00 characterised by the use of electric means
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Feedback Control In General (AREA)
Abstract
The invention discloses a monitoring control system for a cabinet and a control method thereof, which relate to the technical field of monitoring control, wherein the system comprises: the device comprises a processor, a sensor assembly, a temperature adjusting module and a humidity adjusting module; wherein the processor is for controlling the sensor assembly; the sensor assembly comprises a temperature sensor and a humidity sensor; the temperature sensor is used for collecting temperature data of the cabinet; the humidity sensor is used for collecting humidity data of the cabinet; the processor is also used for processing the data acquired by the sensor assembly to obtain a control signal, and the control signal is used for controlling the temperature regulation module and the humidity regulation module; wherein the processor determines the control signal using a PID algorithm. The system monitors and accurately controls the cabinet.
Description
Technical Field
The invention relates to the technical field of monitoring control, in particular to a monitoring control system for a cabinet and a control method thereof.
Background
A cabinet is a freestanding or self-supporting enclosure for housing electrical or electronic equipment. Cabinets are typically configured with doors, removable or non-removable side panels, and back panels.
The cabinet is an integral part of the electrical equipment and is a carrier of the electrical control equipment. Is generally made of cold-rolled steel sheet or alloy. Can provide the protection functions of water resistance, dust resistance, electromagnetic interference resistance and the like for the storage equipment. Cabinets are generally classified as server cabinets, network cabinets, console cabinets, and the like.
The dangerous factors influencing the electronic components are mainly dust, temperature and humidity, so that a constant temperature and humidity system is usually arranged in the cabinet, and the constant temperature and humidity system controls the temperature and humidity and the cleanliness of the environment within a certain fluctuation range so as to meet the requirements of special occasions such as industrial requirements, scientific researches and the like on the environment.
In the environment of a host machine room, monitoring of parameters such as temperature, humidity, smoke and the like is critical to the stable operation of equipment. Excessive temperature, humidity or smoke may cause hardware failures, affecting business continuity. In addition, the machine room typically requires regular inspection and equipment maintenance, which requires a significant amount of labor and time. Therefore, an intelligent system is needed to monitor cabinet environmental parameters in real time and to perform automated control and maintenance depending on the situation.
However, the conventional cabinet detection control system cannot achieve high control accuracy in terms of cold and heat source configuration, air heat and humidity treatment, temperature control and the like of the system, and is liable to cause a decrease in system stability.
Disclosure of Invention
The invention provides a monitoring control system for a cabinet and a control method thereof, which realize the monitoring and accurate control of the system on the cabinet.
According to an aspect of the present disclosure, there is provided a monitoring control system for a cabinet, the system comprising:
the device comprises a processor, a sensor assembly, a temperature adjusting module and a humidity adjusting module; wherein the processor is for controlling the sensor assembly; the sensor assembly comprises a temperature sensor and a humidity sensor;
the temperature sensor is used for collecting temperature data of the cabinet;
the humidity sensor is used for collecting humidity data of the cabinet;
the processor is also used for processing the data acquired by the sensor assembly to obtain a control signal, and the control signal is used for controlling the temperature regulation module and the humidity regulation module;
wherein the processor determines the control signal using a PID algorithm.
In one possible implementation, the processor determines the control signal using a PID algorithm, including:
setting initial parameters of the PID algorithm;
setting a target value and an initial error of temperature and a target value and an initial error of humidity;
Setting an initial value of an accumulated error of the temperature and an initial value of a last error;
acquiring a temperature actual value and a humidity actual value;
calculating the error and accumulated error of temperature, and calculating the error and accumulated error of humidity;
calculating the change rate of temperature and the change rate of humidity;
determining a temperature output signal of a PID algorithm according to the initial parameters, the temperature error and the accumulated error and the temperature change rate;
determining a humidity output signal of a PID algorithm according to the initial parameters, the humidity error and the accumulated error and the humidity change rate;
determining the control signal according to the temperature output signal or the humidity output signal;
the control signal is used for controlling the on or off of the heater, the refrigerator, the dehumidifier or the humidifier.
In one possible implementation, the system further includes: the device comprises a video acquisition module, an audio acquisition module, a display module, an audio output module and a communication module, wherein the processor is further used for controlling the video acquisition module, the audio acquisition module, the display module, the audio output module and the communication module;
the video acquisition module is used for acquiring video data of the machine room;
The audio acquisition module is used for acquiring audio data of the machine room;
the display module is used for displaying the data acquired by the sensor assembly;
the audio output module is used for outputting an audio signal;
the communication module is used for communicating the system with a remote control center.
In one possible implementation, the sensor assembly further includes: an access control sensor, a smoke sensor; the access control sensor is used for sending a signal to the processor when sensing the movement of a person or an object, and the processor sends access control sensing information to the remote control center through the communication module;
the smoke sensor is used for sensing whether smoke exists around the cabinet, when the smoke exists, the smoke sensor sends a signal to the processor, and the processor sends smoke sensing information to the remote control center through the communication module according to the signal sent by the smoke sensor.
In one possible implementation, the video acquisition module includes a camera, the audio acquisition module includes a microphone, the audio output module includes a buzzer and/or a speaker, the system further includes an LED lamp, the buzzer and/or the speaker is used for playing an alarm sound, and the LED lamp is used for: when the system detects abnormal data, a red light is flashed.
In one possible implementation, the system includes a power switch and a fan.
According to an aspect of the present disclosure, there is provided a monitoring control method for a cabinet, the method being applied to the system, the method including:
collecting environment information of a cabinet, wherein the environment information comprises a temperature actual value and a humidity actual value;
determining a control signal according to the environmental information and the PID algorithm, including:
setting initial parameters of the PID algorithm;
setting a target value and an initial error of temperature and a target value and an initial error of humidity;
setting an initial value of an accumulated error of the temperature and an initial value of a last error;
acquiring a temperature actual value and a humidity actual value;
calculating the error and accumulated error of temperature, and calculating the error and accumulated error of humidity;
calculating the change rate of temperature and the change rate of humidity;
determining a temperature output signal of a PID algorithm according to the initial parameters, the temperature error and the accumulated error and the temperature change rate;
determining a humidity output signal of a PID algorithm according to the initial parameters, the humidity error and the accumulated error and the humidity change rate;
determining the control signal according to the temperature output signal or the humidity output signal;
The control signal is used for controlling the on or off of the heater, the refrigerator, the dehumidifier or the humidifier.
The present disclosure provides a monitoring control method for a cabinet, the method being applied to the system, the method comprising:
acquiring training data and test data; the training data and the test data are data related to the environment of the cabinet;
preprocessing the training data and the test data;
constructing a long-short-term memory network model LSTM;
the LSTM model is trained using training data, and model parameters are updated by optimizing the loss function.
In one possible implementation, the preprocessing the training data and the test data includes:
normalizing the data;
sequence division: dividing the time sequence into an input sequence and a target sequence, wherein the input sequence is historical data for prediction, and the target sequence is future data hoped to be predicted;
hysteresis characteristics: using the data of the past time step as an input feature; wherein, the past time step refers to a certain time point before the current time point;
batch generation: the input features are fed into the model in batches for training.
In one possible implementation of the present invention,
The construction of the long-short-time memory network model LSTM comprises the following steps:
constructing an LSTM model using a deep learning framework, comprising: defining LSTM layer, loss function and optimizer.
In one possible implementation, training the LSTM model using training data updates model parameters by optimizing a loss function, comprising:
initializing model parameters: randomly initializing weights and biases of the model before training begins;
forward propagation: for each training sample, sending input data into an LSTM model for forward propagation to obtain a predicted value of the model;
calculating loss: comparing the predicted value of the model with an actual value, and calculating a value of a loss function;
back propagation: the gradient of the model parameters is calculated through the loss function, and counter propagation is carried out to obtain the influence of each parameter on the loss;
parameter updating: updating model parameters according to the gradient information obtained by calculation by using a gradient descent method, so that a loss function is reduced;
repeating the iteration: repeating the steps, and gradually reducing the loss function;
training is finished: the condition for the end of training includes reaching a set point for the number of training steps, or the loss function converging to a certain threshold.
Compared with the prior art, the invention has the beneficial effects that:
in the monitoring control system for the cabinet, when the temperature and the humidity are controlled by the PID algorithm, the current temperature and the humidity data are acquired through the sensor, then the current error is calculated, and the output value of the controller is calculated by the PID control algorithm. According to the output value of the PID control algorithm, the equipment such as a heater, a refrigerator, a humidifier or a dehumidifier can be controlled to realize accurate control of temperature and humidity.
The traditional operation and maintenance mode may require a large amount of personnel investment to perform operations such as manual temperature and humidity monitoring, smoke detection, access control and the like. The multi-mode data cabinet maintenance control system can automatically monitor and control, so that manual operation is reduced, and the burden of operation and maintenance personnel is reduced. Meanwhile, the system can be remotely monitored and controlled, so that the time of operation and maintenance personnel on the site of a machine room is reduced, and the operation and maintenance cost is reduced.
Automatization and accurate control effect:
the system acquires temperature, humidity, smoke and other data through various sensors, and performs real-time environment monitoring and control by utilizing technologies such as PID control algorithm and the like. Compared with manual maintenance, the system can control environmental parameters more accurately and prevent potential problems. For example, the fan, the heater, the refrigerator and other devices can be automatically started and stopped according to the temperature and humidity data, so that the machine room environment is kept in a proper range.
Real-time alarm and remote management:
the system can monitor various parameters in real time and give an alarm in time when abnormal conditions occur. For example, when the temperature is too high or the smoke detects an abnormality, the system can inform related personnel in a short message, mail or the like, so that the problem can be timely handled, and possible hardware damage or faults are avoided. In addition, the system also supports a remote management function, and an operation and maintenance person can remotely monitor and control the cabinet through a mobile phone or a computer without having to physically visit the site.
In a word, the maintenance control system of the multi-mode data cabinet has important application value in the field of maintenance of a host machine room. Through intelligent monitoring, control and management, the system effectively reduces the burden of operation and maintenance personnel, reduces the operation and maintenance cost, realizes accurate environmental control and instant alarm function, and improves the stability and reliability of machine room equipment.
Drawings
Fig. 1 illustrates a block diagram of a monitoring control system for a cabinet in accordance with an embodiment of the present disclosure.
Detailed Description
Various exemplary embodiments, features and aspects of the disclosure will be described in detail below with reference to the drawings. In the drawings, like reference numbers indicate identical or functionally similar elements. Although various aspects of the embodiments are illustrated in the accompanying drawings, the drawings are not necessarily drawn to scale unless specifically indicated.
The word "exemplary" is used herein to mean "serving as an example, embodiment, or illustration. Any embodiment described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments.
In addition, numerous specific details are set forth in the following detailed description in order to provide a better understanding of the present disclosure. It will be understood by those skilled in the art that the present disclosure may be practiced without some of these specific details. In some instances, methods, means, elements, and circuits well known to those skilled in the art have not been described in detail in order not to obscure the present disclosure.
Fig. 1 illustrates a block diagram of a monitoring control system for a cabinet, as shown in fig. 1, according to one embodiment of the present disclosure, the system may include:
the device comprises a processor, a sensor assembly, a temperature adjusting module and a humidity adjusting module; wherein the processor is for controlling the sensor assembly; the sensor assembly may include a temperature sensor and a humidity sensor;
the temperature sensor can be used for collecting temperature data of the cabinet;
the humidity sensor can be used for collecting humidity data of the cabinet;
the processor can also be used for processing the data acquired by the sensor assembly to obtain a control signal, and the control signal is used for controlling the temperature regulation module and the humidity regulation module;
Wherein the processor determines the control signal using a PID algorithm.
Wherein the processor may be a control chip.
The temperature and humidity states of the cabinet can be monitored in real time through the sensor assembly, the control signals are determined through the processor by adopting the PID algorithm, and then the accurate control of the environmental state of the cabinet is realized, the operation efficiency of equipment in the cabinet is improved, and the equipment in the cabinet is more stable in operation.
In one possible implementation, the processor determines the control signal using a PID algorithm, including:
setting initial parameters of the PID algorithm; for example, when the temperature is subjected to the regulation control, the parameters of the PID algorithm are set as: kp_temp=1.0, ki_temp=0.1, kd_temp=0.2, when the humidity is regulated, the parameters of the PID algorithm are set to: kp_hub=1.0, ki_hub=0.1, kd_hub=0.2.
Setting a target value and an initial error of temperature and a target value and an initial error of humidity; for example, the target value of the temperature is set to setpoint_temp=25.0, and the initial error of the temperature is error_temp=0.0; the target value of humidity is set to setpoint_hub=50.0, and the initial error of humidity is error_hub=0.0.
Setting an initial value of the accumulated error of the temperature and an initial value of the last error; for example, the initial value of the cumulative error of the set temperature is integral_temp=0.0, the initial value of the last error of the set temperature is last_error_temp=0.0, the initial value of the cumulative error of the set humidity is integral_hub=0.0, and the last error of the set humidity is last_error_hub=0.0.
Acquiring a temperature actual value and a humidity actual value; for example, the actual value of temperature is actual_temp, and the actual value of humidity is actual_hub.
Calculating the error and accumulated error of temperature, and calculating the error and accumulated error of humidity;
for example, the error of the temperature is calculated by the formula (2), and the accumulated error of the temperature is calculated by the formula (3).
error_temp = setpoint_temp - actual_temp （2）
integral_temp = integral_temp + error_temp （3）
For example, the error of humidity is calculated by the formula (4), and the integrated error of humidity is calculated by the formula (5).
error_humid = setpoint_humid - actual_humid （4）
integral_humid = integral_humid + error_humid （5）
Calculating the change rate of temperature and the change rate of humidity;
for example, the rate of change of temperature and the rate of change of humidity by the formula (7) are calculated by the formula (6)
rate_of_change_temp = error_temp - last_error_temp （6）
rate_of_change_humid = error_humid - last_error_humid （7）
The PID algorithm output for calculating the temperature and the humidity, for example, the PID algorithm output for calculating the temperature by the formula (8), the PID algorithm output for calculating the humidity by the formula (9).
output_temp = kp_temp error_temp + ki_temp /> integral_temp + kd_temp /> rate_of_change_temp （8）
output_humid = kp_humid error_humid + ki_humid /> integral_humid + kd_humid /> rate_of_change_humid （9）
Determining a temperature output signal of a PID algorithm according to the initial parameters, the temperature error and the accumulated error and the temperature change rate;
Determining a humidity output signal of a PID algorithm according to the initial parameters, the humidity error and the accumulated error and the humidity change rate;
determining the control signal according to the temperature output signal or the humidity output signal;
for example, if the output_temp is greater than zero, the control signal is a control signal to turn on the heater, otherwise the control signal is a control signal to turn off the heater.
The control signal is a control signal to turn on the refrigerator if the output_temp is less than zero, otherwise the control signal is a control signal to turn off the refrigerator.
If the output_limit is greater than zero, the control signal is a control signal to turn on the humidifier, otherwise the control signal is a control signal to turn off the humidifier.
If the output_hub is less than zero, the control signal is a control signal to turn on the dehumidifier, otherwise the control signal is a control signal to turn off the dehumidifier.
The control signal is used for controlling the on or off of the heater, the refrigerator, the dehumidifier or the humidifier.
For example, a heater, a refrigerator, a humidifier, or a dehumidifier is controlled according to the controller to achieve accurate control of temperature and humidity.
For example, the PID control algorithm is a classical control algorithm, the name of which derives from the initials of three english words, proportional (pro), integral (Integral) and Derivative (Derivative). The basic idea is to realize accurate control of the control object by continuously measuring and adjusting the error of the control object. The PID control algorithm calculates the output of the controller according to the error, the error accumulation and the error change rate, and controls the system through the output, so that the control effect is good.
The formula of the PID control algorithm is as follows (1):
（1）
where u (t) is the output value of the controller, e (t) is the control error, i.e. the difference between the desired value and the actual value,，/>and->The parameters corresponding to the proportional, integral and differential controllers are used for adjusting the response speed, stability and anti-interference capability of the controller.
When the PID algorithm is used for controlling the temperature and the humidity, the current temperature and the humidity data are acquired through the sensor, then the current error is calculated, and the output value of the controller is calculated by using the PID control algorithm. According to the output value of the PID control algorithm, the equipment such as a heater, a refrigerator, a humidifier or a dehumidifier can be controlled to realize accurate control of temperature and humidity.
In one possible implementation, the sensor assembly further includes: an access control sensor, a smoke sensor; the access control sensor is used for sending a signal to the processor when sensing the movement of a person or an object, and the processor sends access control sensing information to the remote control center through the communication module;
the smoke sensor is used for sensing whether smoke exists around the cabinet, when the smoke exists, the smoke sensor sends a signal to the processor, and the processor sends smoke sensing information to the remote control center through the communication module according to the signal sent by the smoke sensor.
In one possible implementation, the system further includes: the device comprises a video acquisition module, an audio acquisition module, a display module, an audio output module and a communication module, wherein the processor is further used for controlling the video acquisition module, the audio acquisition module, the display module, the audio output module and the communication module;
the video acquisition module is used for acquiring video data of the machine room; for example, when the entrance guard sensor detects movement of a person or an object, a camera is started to record video for storing monitoring video data.
The audio acquisition module is used for acquiring audio data of the machine room;
the display module is used for displaying the data acquired by the sensor assembly;
the audio output module is used for outputting an audio signal;
the communication module is used for communicating the system with a remote control center.
A user may monitor and control a cabinet, such as a remote switching power supply, modifying control logic, etc., through a cloud management platform.
In one possible implementation, the video acquisition module includes a camera, the audio acquisition module includes a microphone, the audio output module includes a buzzer and/or a speaker, the system further includes an LED lamp, the buzzer and/or the speaker is used for playing an alarm sound, and the LED lamp is used for: when the system detects abnormal data, a red light is flashed.
For example, camera movement, such as angular rotation, may be controlled based on video data collected by the camera.
For example, when the temperature or the humidity is abnormal, the alarm is given by the buzzer, and the on-site staff is prompted to check by the flashing of the LED lamp.
In one possible implementation, the system includes a power switch and a fan.
In one possible implementation, the switching of the power supply of the monitoring system may be controlled by a remote control center.
In one possible implementation, the processor may implement digital signal processing, image processing, speech recognition, and the like.
Developing control software: according to the architecture design, a set of control software is developed to support various data inputs and outputs. The user can monitor the state of the cabinet, such as temperature, humidity, door access state, etc., through the software, and can perform control operations, such as switching power supply, starting fans, etc.
Integrating cloud management functions: and integrating the cabinet maintenance control system into a cloud management platform to support remote monitoring and control. A user may monitor and control a cabinet, such as a remote switching power supply, modifying control logic, etc., through a cloud management platform.
Testing and debugging: and after the installation and integration are finished, performing system testing and debugging. The tests comprise a function test, a performance test, a stability test and the like, so that the system can work normally and meet the requirements of users.
Deployment and maintenance: after testing and debugging are finished, the system is deployed into an actual use environment, and maintenance and upgrading are carried out regularly. Maintenance includes hardware fault processing, software upgrading, data backup and the like, and ensures that the system operates stably and reliably.
When designing a control system for input and output of multi-modal data, the following aspects need to be considered:
data input: the system needs to support a variety of data inputs such as sensor data, video data, audio data, etc. The sensor data may be input by analog input or digital input, and the video data and the audio data may be input by a camera and a microphone.
And (3) data processing: the system needs to support a variety of data processing methods such as digital signal processing, image processing, speech recognition, etc. The data processing can be performed locally or at the cloud.
And (3) data output: the system needs to support a variety of data output modes such as displays, speakers, LED lights, etc. The output device may be directly connected to the control system or may be remotely output via a network connection.
Control logic: the system needs to design a set of control logic, and judges and controls output according to input data. For example, temperature and humidity are controlled based on sensor data, camera movement is controlled based on video data, and the like.
The present disclosure provides a monitoring control method for a cabinet, the method being used for the monitoring control system, the method comprising:
Collecting environment information of a cabinet, wherein the environment information comprises a temperature actual value and a humidity actual value;
determining a control signal according to the environmental information and the PID algorithm, including:
setting initial parameters of the PID algorithm;
setting a target value and an initial error of temperature and a target value and an initial error of humidity;
setting an initial value of an accumulated error of the temperature and an initial value of a last error;
acquiring a temperature actual value and a humidity actual value;
calculating the error and accumulated error of temperature, and calculating the error and accumulated error of humidity;
calculating the change rate of temperature and the change rate of humidity;
determining a temperature output signal of a PID algorithm according to the initial parameters, the temperature error and the accumulated error and the temperature change rate;
determining a humidity output signal of a PID algorithm according to the initial parameters, the humidity error and the accumulated error and the humidity change rate;
determining the control signal according to the temperature output signal or the humidity output signal;
the control signal is used for controlling the on or off of the heater, the refrigerator, the dehumidifier or the humidifier.
According to the output value of the PID control algorithm, the equipment such as a heater, a refrigerator, a humidifier or a dehumidifier can be controlled to realize accurate control of temperature and humidity.
The present disclosure provides a monitoring control method for a cabinet, the method being applied to the system, the method comprising:
acquiring training data and test data; the training data and the test data are data related to the environment of the cabinet;
preprocessing the training data and the test data;
constructing a long-short-term memory network model LSTM;
the LSTM model is trained using training data, and model parameters are updated by optimizing the loss function.
In one possible implementation, the preprocessing the training data and the test data includes:
normalizing the data;
sequence division: dividing the time sequence into an input sequence and a target sequence, wherein the input sequence is historical data for prediction, and the target sequence is future data hoped to be predicted;
hysteresis characteristics: using the data of the past time step as an input feature; wherein, the past time step refers to a certain time point before the current time point;
batch generation: the input features are fed into the model in batches for training.
In one possible implementation of the present invention,
the construction of the long-short-time memory network model LSTM comprises the following steps:
constructing an LSTM model using a deep learning framework, comprising: defining LSTM layer, loss function and optimizer.
In one possible implementation, training the LSTM model using training data updates model parameters by optimizing a loss function, comprising:
initializing model parameters: randomly initializing weights and biases of the model before training begins;
forward propagation: for each training sample, sending input data into an LSTM model for forward propagation to obtain a predicted value of the model;
calculating loss: comparing the predicted value of the model with an actual value, and calculating a value of a loss function;
back propagation: the gradient of the model parameters is calculated through the loss function, and counter propagation is carried out to obtain the influence of each parameter on the loss;
parameter updating: updating model parameters according to the gradient information obtained by calculation by using a gradient descent method, so that a loss function is reduced;
repeating the iteration: repeating the steps, and gradually reducing the loss function;
training is finished: the condition for the end of training includes reaching a set point for the number of training steps, or the loss function converging to a certain threshold.
The control key point of the system is that: intelligent prediction and optimization:
the intelligent prediction function of the system refers to:
environmental changes and equipment faults which are likely to happen later are predicted by utilizing historical data and a machine learning algorithm, so that measures are taken in advance. In addition, the optimization algorithm may automatically adjust the control parameters to achieve better performance.
In the aspect of adopting a machine learning model to strengthen intelligent prediction and optimization, the system uses time sequence analysis for predicting future environmental changes and equipment faults. The model is trained from historical data so that it can accurately predict future conditions.
In an intelligent prediction and optimization system for a multi-modal data rack, a time series prediction model, a long and short time memory network (LSTM), is used to predict changes in environmental parameters. LSTM is a cyclic neural network (RNN) variant suitable for sequence data, which performs well in processing time series data, is capable of capturing long-term dependencies, and is therefore suitable for predicting future environmental parameter changes.
Implementing a long-short-term memory network (LSTM) model:
the steps are as follows:
data preparation: training data and test data are prepared, and data are preprocessed and feature engineering is performed.
Data sources: the data source may be time series data such as observations of environmental parameters such as temperature, humidity, air pressure, etc.
Data format: the data format is a two-dimensional array, where rows represent time steps and columns represent different features or variables. For univariate time series, a one-dimensional array is created, listed as time steps. For a multivariate time series, each feature is a separate column.
1.3. Pretreatment:
1.3.1 normalization or normalization
1.3.2 The sequence division divides the time sequence into an input sequence and a target sequence. The input sequence is historical data for prediction and the target sequence is future data that is desired to be predicted
1.3.3 Hysteresis features, i.e. using data of past time steps as input features
1.3.4 Batch generation trains data batch (batch) into a model to improve computational efficiency
And (3) constructing a model: the LSTM model is built using a deep learning framework (e.g., tensorFlow, pyTorch), including defining LSTM layers, loss functions, optimizers, and the like.
3. Model training: the LSTM model is trained using training data, and model parameters are updated by optimizing the loss function.
The system is characterized in that the model can gradually approach the expected output by updating the model parameters:
loss Function (Loss Function): the loss function is a measure of the difference between the model predicted value and the actual value. During the training process, the goal of the model is to reduce the prediction error by minimizing the loss function. For regression problems, the system uses the mean square error (Mean Squared Error, MSE) as the loss function
；
Optimization algorithm (Optimization Algorithm): the optimization algorithm is used to update the model parameters so that the loss function gradually decreases. The optimization algorithm used by the present system is Gradient Descent (Gradient Descent). The basic idea of the gradient descent method is to update the model parameters in the opposite direction of the gradient of the loss function, thereby finding local minima.
And (3) injection: the gradient descent method is an optimization algorithm that updates model parameters to minimize the loss function. In machine learning and deep learning, we typically make it better to fit training data by adjusting the parameters of the model in order to have better performance on the test data. The gradient descent method is a basic iterative method, and uses gradient information of a loss function on model parameters to guide the updating direction of the parameters, so that the loss is gradually reduced.
Model training:
initializing model parameters: the weights and biases of the model need to be randomly initialized before training begins.
1. ) Forward propagation: and for each training sample, sending the input data into an LSTM model for forward propagation to obtain a predicted value of the model.
2) Calculating loss: the predicted value of the model is compared with the actual value and the value of the loss function is calculated.
3) Back propagation: and (3) carrying out back propagation by calculating the gradient of the loss function on the model parameters to obtain the influence of each parameter on the loss. This step uses the chain law to propagate the error from the output layer back to each neuron, calculating the gradient.
4) Parameter updating: and updating model parameters according to the calculated gradient information by using an optimization algorithm (such as a gradient descent method) so as to reduce a loss function.
5) Repeating the iteration: repeating the steps to gradually reduce the loss function. Each iteration is referred to as a training step (training step) or an epoch. The number of training steps is typically defined, as well as the training sample batch size used in each training step.
6) Training is finished: the condition for the termination of training may be that a certain number of training steps is reached or that the loss function converges to a certain threshold. After a sufficient number of training steps, the model parameters will gradually adjust to minimize the loss.
The deep learning frameworks such as TensorFlow and PyTorch provide built-in optimizers and automatic derivation functions, so that the LSTM model training process is simpler and more convenient. By performing forward propagation, computational loss, backward propagation, and parameter updates in each training step, the model will learn the patterns and features of the data step by step for better prediction.
4. Model evaluation: and evaluating the trained model by using the test data, and calculating the error between the predicted result and the actual result.
5. And (3) predicting: future data is predicted using the trained LSTM model.
The use of intelligent predictive functionality can have a number of positive effects in a multi-modal data rack maintenance control system:
Predicting failure and maintenance requirements: the intelligent prediction function may analyze the historical data to identify potential failure modes and anomalies. In this way, the system can predict possible faults in advance and take appropriate maintenance measures before the fault occurs, thereby reducing equipment downtime and maintenance costs.
Optimizing resource allocation: the predictive model may predict future data loads and demands to help optimize resource allocation and scheduling. The system may allocate more resources to the time period for which more processing power is expected to be needed based on the prediction result.
Energy saving and resource utilization rate improvement: based on intelligent predictions, the system can adjust the operating mode and settings of the device to reduce unnecessary energy consumption and resource waste. This helps to reduce energy costs and increase resource utilization.
Early overload prevention: predicting future loads may help the system take action before the load approaches an overload condition, preventing the server or network device from crashing or degrading performance under high load conditions.
Enhancing user experience: by predicting the user behavior and demand, the system can respond in advance to provide faster and more accurate service, thereby improving the user experience.
The manual intervention is reduced: the intelligent prediction can automate the decision process, reducing the need for manual intervention. The operation and maintenance personnel can concentrate on solving the more complex problem and improve the operation and maintenance efficiency.
Data driven decision: the intelligent prediction provides data-based support for decision making, so that the decision making is more basic and can be more suitable for actual conditions.
Risk reduction: by predicting potential problems, the system can reduce the occurrence of accidents, thereby reducing business risks.
The intelligent prediction function can help the multi-mode data cabinet maintenance control system to be more intelligent and efficient, provide better data driving decision and resource management, reduce downtime, reduce maintenance cost, promote user experience, and make a more confident decision when facing unknown conditions.
It should be noted that, for simplicity of description, the foregoing method embodiments are all described as a series of acts, but it should be understood by those skilled in the art that the present disclosure is not limited by the order of acts described, as some steps may be performed in other orders or concurrently in accordance with the present disclosure. Further, those skilled in the art will also appreciate that the embodiments described in the specification are all alternative embodiments, and that the acts and modules referred to are not necessarily required by the present disclosure.
In the foregoing embodiments, the descriptions of the embodiments are emphasized, and for parts of one embodiment that are not described in detail, reference may be made to related descriptions of other embodiments.
In the several embodiments provided in the present disclosure, it should be understood that the disclosed apparatus may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, such as the division of the units, merely a logical function division, and there may be additional manners of dividing the actual implementation, such as multiple units or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, or may be in electrical or other forms.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in each embodiment of the present disclosure may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units described above may be implemented either in hardware or in software program modules.
The integrated units, if implemented in the form of software program modules, may be stored in a computer-readable memory for sale or use as a stand-alone product. Based on such understanding, the technical solution of the present disclosure may be embodied in essence or a part contributing to the prior art or all or part of the technical solution in the form of a software product stored in a memory, comprising several instructions for causing a computer device (which may be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in the various embodiments of the present disclosure. And the aforementioned memory includes: a U-disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a removable hard disk, a magnetic disk, or an optical disk, or other various media capable of storing program codes.
Those of ordinary skill in the art will appreciate that all or a portion of the steps in the various methods of the above embodiments may be implemented by a program that instructs associated hardware, and the program may be stored in a computer readable memory, which may include: flash disk, read-Only Memory (ROM), random access Memory (Random Access Memory, RAM), magnetic disk or optical disk.
The foregoing has described in detail embodiments of the present disclosure, with specific examples being employed herein to illustrate the principles and implementations of the present disclosure, the above examples being provided solely to assist in understanding the methods of the present disclosure and their core ideas; meanwhile, as one of ordinary skill in the art will have variations in the detailed description and the application scope in light of the ideas of the present disclosure, the present disclosure should not be construed as being limited to the above description.
Various aspects of the present disclosure are described herein with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the disclosure. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer-readable program instructions.
The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of instructions, which comprises one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The foregoing description of the embodiments of the present disclosure has been presented for purposes of illustration and description, and is not intended to be exhaustive or limited to the embodiments disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the various embodiments described. The terminology used herein was chosen in order to best explain the principles of the embodiments, the practical application, or the technical improvements in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein.
Claims (10)
1. A monitoring control system for a cabinet, the system comprising:
the device comprises a processor, a sensor assembly, a temperature adjusting module and a humidity adjusting module; wherein the processor is for controlling the sensor assembly; the sensor assembly comprises a temperature sensor and a humidity sensor;
the temperature sensor is used for collecting temperature data of the cabinet;
the humidity sensor is used for collecting humidity data of the cabinet;
the processor is also used for processing the data acquired by the sensor assembly to obtain a control signal, and the control signal is used for controlling the temperature regulation module and the humidity regulation module;
wherein the processor determines the control signal using a PID algorithm.
2. The monitoring control system for a cabinet of claim 1, wherein the processor determines the control signal using a PID algorithm, comprising:
setting initial parameters of the PID algorithm;
setting a target value and an initial error of temperature and a target value and an initial error of humidity;
setting an initial value of an accumulated error of the temperature and an initial value of a last error;
acquiring a temperature actual value and a humidity actual value;
Calculating the error and accumulated error of temperature, and calculating the error and accumulated error of humidity;
calculating the change rate of temperature and the change rate of humidity;
determining a temperature output signal of a PID algorithm according to the initial parameters, the temperature error and the accumulated error and the temperature change rate;
determining a humidity output signal of a PID algorithm according to the initial parameters, the humidity error and the accumulated error and the humidity change rate;
determining the control signal according to the temperature output signal or the humidity output signal;
the control signal is used for controlling the on or off of the heater, the refrigerator, the dehumidifier or the humidifier.
3. The monitoring and control system for a cabinet of claim 1, further comprising: the device comprises a video acquisition module, an audio acquisition module, a display module, an audio output module and a communication module, wherein the processor is further used for controlling the video acquisition module, the audio acquisition module, the display module, the audio output module and the communication module;
the video acquisition module is used for acquiring video data of the machine room;
the audio acquisition module is used for acquiring audio data of the machine room;
The display module is used for displaying the data acquired by the sensor assembly;
the audio output module is used for outputting an audio signal;
the communication module is used for communicating the system with a remote control center.
4. A monitoring and control system for a cabinet according to claim 3, wherein the sensor assembly further comprises: an access control sensor, a smoke sensor; the access control sensor is used for sending a signal to the processor when sensing the movement of a person or an object, and the processor sends access control sensing information to the remote control center through the communication module;
the smoke sensor is used for sensing whether smoke exists around the cabinet, when the smoke exists, the smoke sensor sends a signal to the processor, and the processor sends smoke sensing information to the remote control center through the communication module according to the signal sent by the smoke sensor.
5. The monitoring control system for a cabinet of claim 4, wherein the video acquisition module comprises a camera, the audio acquisition module comprises a microphone, the audio output module comprises a buzzer and/or a speaker, the system further comprises an LED light for playing an alarm sound, the LED light for: when the system detects abnormal data, a red light is flashed.
6. A method for monitoring and controlling a cabinet, the method being applied to the system of any one of claims 1 to 5, the method comprising:
collecting environment information of a cabinet, wherein the environment information comprises a temperature actual value and a humidity actual value;
determining a control signal according to the environmental information and the PID algorithm, including:
setting initial parameters of the PID algorithm;
setting a target value and an initial error of temperature and a target value and an initial error of humidity;
setting an initial value of an accumulated error of the temperature and an initial value of a last error;
acquiring a temperature actual value and a humidity actual value;
calculating the error and accumulated error of temperature, and calculating the error and accumulated error of humidity;
calculating the change rate of temperature and the change rate of humidity;
determining a temperature output signal of a PID algorithm according to the initial parameters, the temperature error and the accumulated error and the temperature change rate;
determining a humidity output signal of a PID algorithm according to the initial parameters, the humidity error and the accumulated error and the humidity change rate;
determining the control signal according to the temperature output signal or the humidity output signal;
the control signal is used for controlling the on or off of the heater, the refrigerator, the dehumidifier or the humidifier.
7. A method for monitoring and controlling a cabinet, the method being applied to the system of any one of claims 1 to 5, the method comprising:
acquiring training data and test data; the training data and the test data are data related to the environment of the cabinet;
preprocessing the training data and the test data;
constructing a long-short-term memory network model LSTM;
the LSTM model is trained using training data, and model parameters are updated by optimizing the loss function.
8. The method of claim 7, wherein the preprocessing the training data and the test data comprises:
normalizing the data;
sequence division: dividing the time sequence into an input sequence and a target sequence, wherein the input sequence is historical data for prediction, and the target sequence is future data hoped to be predicted;
hysteresis characteristics: using the data of the past time step as an input feature; wherein, the past time step refers to a certain time point before the current time point;
batch generation: the input features are fed into the model in batches for training.
9. The method for monitoring and controlling a cabinet according to claim 8, wherein,
The construction of the long-short-time memory network model LSTM comprises the following steps:
constructing an LSTM model using a deep learning framework, comprising: defining LSTM layer, loss function and optimizer.
10. The method of claim 9, wherein,
training the LSTM model using the training data to update model parameters by optimizing the loss function, comprising:
initializing model parameters: randomly initializing weights and biases of the model before training begins;
forward propagation: for each training sample, sending input data into an LSTM model for forward propagation to obtain a predicted value of the model;
calculating loss: comparing the predicted value of the model with an actual value, and calculating a value of a loss function;
back propagation: the gradient of the model parameters is calculated through the loss function, and counter propagation is carried out to obtain the influence of each parameter on the loss;
parameter updating: updating model parameters according to the gradient information obtained by calculation by using a gradient descent method, so that a loss function is reduced;
repeating the iteration: repeating the steps, and gradually reducing the loss function;
training is finished: the condition for the end of training includes reaching a set point for the number of training steps, or the loss function converging to a certain threshold.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311047503.XA CN116755497A (en) | 2023-08-21 | 2023-08-21 | Monitoring control system for cabinet and control method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311047503.XA CN116755497A (en) | 2023-08-21 | 2023-08-21 | Monitoring control system for cabinet and control method thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116755497A true CN116755497A (en) | 2023-09-15 |
Family
ID=87957616
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311047503.XA Pending CN116755497A (en) | 2023-08-21 | 2023-08-21 | Monitoring control system for cabinet and control method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116755497A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150237908A1 (en) * | 2014-02-26 | 2015-08-27 | Henny Penny Corporation | Holding cabinets, methods for controlling environmental conditions in holding cabinets, and computer-readable media storing instructions for implementing such methods |
| CN104991496A (en) * | 2015-07-10 | 2015-10-21 | 中国电子科技集团公司第二十八研究所 | Cabinet environment intelligent detection and control device and method |
| CN205353820U (en) * | 2015-12-31 | 2016-06-29 | 南京科达新控仪表有限公司 | Rack atmospheric control system for heat exchange station |
| US20160291605A1 (en) * | 2013-11-21 | 2016-10-06 | Zte Corporation | Method, and device for controlling the output of the air volume and memory medium |
| CN107769972A (en) * | 2017-10-25 | 2018-03-06 | 武汉大学 | A kind of power telecom network equipment fault Forecasting Methodology based on improved LSTM |
| CN207937833U (en) * | 2018-04-12 | 2018-10-02 | 福州冠博电子科技有限公司 | A kind of electronic sand table feeding back cabinet equipment working condition |
| CN108919862A (en) * | 2018-07-12 | 2018-11-30 | 中国船舶重工集团公司第七二四研究所 | A kind of automatic temperature/humidity control method of airtight cabinet based on temperature feedback |
-
2023
- 2023-08-21 CN CN202311047503.XA patent/CN116755497A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160291605A1 (en) * | 2013-11-21 | 2016-10-06 | Zte Corporation | Method, and device for controlling the output of the air volume and memory medium |
| US20150237908A1 (en) * | 2014-02-26 | 2015-08-27 | Henny Penny Corporation | Holding cabinets, methods for controlling environmental conditions in holding cabinets, and computer-readable media storing instructions for implementing such methods |
| CN104991496A (en) * | 2015-07-10 | 2015-10-21 | 中国电子科技集团公司第二十八研究所 | Cabinet environment intelligent detection and control device and method |
| CN205353820U (en) * | 2015-12-31 | 2016-06-29 | 南京科达新控仪表有限公司 | Rack atmospheric control system for heat exchange station |
| CN107769972A (en) * | 2017-10-25 | 2018-03-06 | 武汉大学 | A kind of power telecom network equipment fault Forecasting Methodology based on improved LSTM |
| CN207937833U (en) * | 2018-04-12 | 2018-10-02 | 福州冠博电子科技有限公司 | A kind of electronic sand table feeding back cabinet equipment working condition |
| CN108919862A (en) * | 2018-07-12 | 2018-11-30 | 中国船舶重工集团公司第七二四研究所 | A kind of automatic temperature/humidity control method of airtight cabinet based on temperature feedback |
Non-Patent Citations (3)
| Title |
|---|
| 深度学习/DL: "《如何理解LSTM，对于一个时序序列，他是怎么训练的？》", Retrieved from the Internet <URL:https://www.zhihu.com/question/298579013/answer/3193512848> * |
| 王林: "《Python中的LSTM模型详解》", Retrieved from the Internet <URL:https://www.php.cn/faq/557471.html> * |
| 高潭华、卢道明: "《大学物理实验》", 同济大学出版社, pages: 111 - 112 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP7017861B2 (en) | Anomaly detection system and anomaly detection method | |
| US11592800B2 (en) | Abnormality detector of a manufacturing machine using machine learning | |
| JP2021064370A (en) | Method and system for semi-supervised deep abnormality detection for large-scale industrial monitoring system based on time-series data utilizing digital twin simulation data | |
| WO2019245728A1 (en) | Deep-learning-based fault detection in building automation systems | |
| RU2626780C1 (en) | Method and system of remote monitoring energy installations | |
| US10047757B2 (en) | Predicting a surge event in a compressor of a turbomachine | |
| Yoshida et al. | ARX and AFMM model-based on-line real-time data base diagnosis of sudden fault in AHU of VAV system | |
| WO2019133316A1 (en) | Reconstruction-based anomaly detection | |
| EP2946219B2 (en) | Method, apparatus and computer-program product for determining faults in a lighting system | |
| KR102114895B1 (en) | Building automatic control system and method for predicting aging time of facilities in buildings based on energy efficiency of facilities in buildings | |
| EP3904987B1 (en) | Control support apparatus, control support method, control support program, computer readable medium with control support program recorded thereon and control system | |
| US20210232104A1 (en) | Method and system for identifying and forecasting the development of faults in equipment | |
| CN110764474A (en) | Method and system for monitoring running state of equipment | |
| Kumar et al. | Development of parameter based fault detection and diagnosis technique for energy efficient building management system | |
| WO2018016098A1 (en) | Facility monitoring device and facility monitoring method | |
| Lutska et al. | Forecasting the efficiency of the control system of the technological object on the basis of neural networks | |
| AU2018426458B2 (en) | Assistance device, learning device, and plant operation condition setting assistance system | |
| US20220201374A1 (en) | Data processing system, data processing method, program, sensor apparatus, and receiving apparatus | |
| CN116755497A (en) | Monitoring control system for cabinet and control method thereof | |
| US11339763B2 (en) | Method for windmill farm monitoring | |
| CN114970950A (en) | Fan fault alarm method and device, storage medium and electronic equipment | |
| JP7418157B2 (en) | Equipment monitoring device and equipment monitoring method | |
| JP2022134340A (en) | Peripheral apparatus, monitoring system, monitoring method, and program | |
| KR20010036423A (en) | Method and apparatus for detecting fault using General Regression Neural Network | |
| KR102443273B1 (en) | Building automatic control apparatus capable of energy optimization and facility operation efficiency using data analysis method and method of the same |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |