Factory electrical equipment control system based on Internet of Things

Abstract

The invention discloses a factory electrical equipment control system based on the Internet of Things, relates to the technical field of the Internet of Things, and is used for improving the problem that the power supply efficiency is reduced due to a carbon deposition phenomenon caused by insufficient combustion of a standby generator. Comparing a normal stable interval to judge whether the standby generator generates abnormal heating or not, if not, collecting the vibration frequency of a standby generator bearing and the sound frequency in a power supply state, and performing wear evaluation on the standby generator bearing by using a random forest algorithm according to the vibration frequency and sound frequency change of the standby generator. The carbon deposition amount of the power supply chamber is detected, the power supply state of the standby generator is determined by integrating the bearing wear evaluation result of the standby generator and the carbon deposition amount of the power supply chamber, and the power supply rate of the current-carrying conductor is detected in real time; power supply or power-off alarm is selected according to the power supply state of the standby generator and the power supply rate of the current-carrying conductor so as to guarantee the power supply environment of the standby generator.

Description

Technical Field

[0001] The present invention relates to the technical field of Internet of Things, and more specifically, to a plant electrical equipment control system based on the Internet of Things. Background Art

[0002] Internet of Things technology refers to connecting objects to the network through information sensing equipment, realizing the connection between things and realizing intelligent identification, supervision, regulation and other functions. Applying Internet of Things technology to the control of factory electrical equipment can increase the service life of electrical equipment and ensure the safety of the operating environment of electrical equipment.

[0003] The existing technology has the following deficiencies: In the past, the factory's backup generators would not start when the mains power was normally supplied. When the mains power was abnormal and caused a power outage in the factory, the backup generators that had not been started for a long time would cause incomplete combustion and cause carbon deposition, resulting in low power supply efficiency and increased safety risks in the power generation environment. Summary of the Invention

[0004] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a factory electrical equipment control system based on the Internet of Things, which determines the power supply status of the standby generator by detecting the power supply temperature and analyzing the degree of bearing wear and the amount of carbon deposits of the standby generator. In combination with the power supply rate of the current-carrying conductor in the power supply status, an alarm rule is formulated to perform power supply or power-off alarm to solve the problems raised in the above-mentioned background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions: The IoT-based factory electrical equipment control system includes: data acquisition module, abnormality judgment module, power supply assessment module and response alarm module, and signal connections between each module; The data acquisition module is used to detect the power supply temperature of the standby generator in real time and transmit it to the abnormality judgment module. When receiving the normal power supply temperature signal, it detects the amount of carbon deposits in the power supply room and collects the vibration frequency of the standby generator bearing and the sound frequency under the power supply state and transmits them together to the power supply evaluation module. After receiving the status signal sent by the power supply evaluation module, it continuously detects the power supply rate of the current-carrying conductor and transmits the detection data to the response alarm module; The abnormality judgment module is used to receive the power supply temperature of the standby generator and compare it with the normal power supply temperature range of the standby generator in the monitoring system database to determine whether the power supply temperature of the standby generator is abnormal. According to the judgment result, an abnormal power supply temperature signal or a normal power supply temperature signal is set, and the normal power supply temperature signal is transmitted back to the data acquisition module, and the abnormal power supply temperature signal is transmitted to the response alarm module; The power supply assessment module is used to receive the amount of carbon deposits in the power supply room, the vibration frequency of the standby generator bearing, and the sound frequency under the power supply state. The module uses a random forest algorithm to assess the wear of the standby generator bearing based on the vibration frequency of the standby generator and the frequency of sound changes under the power supply state. The power supply state of the standby generator is determined based on the comprehensive assessment results of the bearing wear of the standby generator and the amount of carbon deposits in the power supply room. The status signal is set to be transmitted to the data acquisition module and the response alarm module according to the power supply state of the standby generator. The response alarm module is used to receive the power supply rate detection result and status signal of the current-carrying conductor and set the alarm rules, and perform power supply, alarm or power off response processing according to the alarm rules.

[0006] In a preferred embodiment, the data acquisition module determines the amount of carbon deposits in the power supply chamber by detecting the concentration of carbon monoxide in the power supply chamber; The data acquisition module selects a period of time as the detection time before collecting the vibration frequency of the standby generator bearing, divides the detection time into N equal parts, and regards each time as a time group. The vibration frequency of the standby generator bearing in each time group is collected by the vibration spectrum analyzer, and the average value is taken as the bearing vibration frequency of the corresponding time group; When the data acquisition module collects the sound frequency in the power supply state, it detects the sound frequency obtained in each time group, selects the maximum and minimum sound frequencies in the corresponding time group, takes the difference between the maximum and minimum sound frequencies in each time group to obtain the sound change frequency of the corresponding time group, and transmits the bearing vibration frequency and sound change frequency of each time group to the power supply evaluation module.

[0007] In a preferred embodiment, the abnormality judgment module accesses the monitoring system database to determine the normal power supply temperature range of the standby generator, and compares the power supply temperature of the standby generator input through the data acquisition module with the normal power supply temperature range of the standby generator to set the power supply temperature signal. When the power supply temperature of the standby generator is within the normal power supply temperature range of the standby generator, it is judged that the power supply of the standby generator is normal, and the power supply temperature signal is set to the normal power supply temperature signal; when the power supply temperature of the standby generator is outside the normal power supply temperature range of the standby generator, it is judged that the power supply of the standby generator is abnormal, and the power supply temperature signal is set to the abnormal power supply temperature signal.

[0008] In a preferred embodiment, the abnormality judgment module transmits the normal power supply temperature signal back to the data acquisition module. When the data acquisition module receives the normal power supply temperature signal, it detects the amount of carbon deposits in the power supply room and collects the vibration frequency of the standby generator bearing and the sound frequency under the power supply state. If the normal power supply temperature signal is not received, no data collection is performed.

[0009] In a preferred embodiment, after receiving the bearing vibration frequency and sound change frequency of each time group, the power supply assessment module uses the random forest algorithm to perform wear assessment on the standby generator bearing. The specific steps are as follows: Feature confirmation: Bearing vibration frequency and sound change frequency are used as input features, and wear assessment is defined as output feature; Data preprocessing: Merge each time group as one data into the input feature dataset; Data segmentation: Split the input feature dataset into training and test sets; Data processing: randomly extract multiple data from the training set, and use each extracted data as a training sample; randomly extract multiple data from the test set, and use each extracted data as a test sample; Construct a decision tree: For each training sample and test sample, construct a decision tree. At each node of the tree, randomly select one or more input features from the training sample or test sample to store; Establishing a feature selection threshold: Count the number of occurrences of each input feature in all decision trees in the training sample, and use the ratio of the number of occurrences of the input feature to the number of occurrences of all input features as the weight of the corresponding input feature. Normalize the input features in each training sample and take the weighted sum as the feature selection threshold. Screening feature selection threshold: Use test samples to set feature comparison thresholds, and screen feature selection thresholds based on the feature comparison thresholds; Wear assessment: The received bearing vibration frequency and sound change frequency are normalized and then summed to take the average value as the bearing wear coefficient of the standby generator. The wear coefficient of the standby generator is compared with the feature selection threshold for wear assessment.

[0010] In a preferred embodiment, the specific steps of screening the feature selection threshold are as follows: The number of occurrences of each input feature in all decision trees in the test sample is counted, and the ratio of the number of occurrences of the input feature to the number of occurrences of all input features is used as the weight of the corresponding input feature. The input features in each test sample are normalized and then weighted summed as the feature comparison threshold. The feature comparison threshold is subtracted from the feature selection threshold and then compared with the preset screening coefficient. When the difference result is lower than the screening coefficient, the feature selection threshold is retained; when the difference result exceeds the screening coefficient, the decision tree is reconstructed, and the bearing vibration frequency or sound change frequency or both input features are randomly stored in each node.

[0011] In a preferred embodiment, when the wear coefficient of the standby generator exceeds the feature selection threshold, the standby generator bearing is judged to be severely worn; when the wear coefficient of the standby generator is lower than the feature selection threshold, the standby generator bearing is judged to be slightly worn.

[0012] In a preferred embodiment, the specific steps of determining the power supply status of the standby generator by combining the bearing wear assessment results of the standby generator and the amount of carbon deposits in the power supply chamber are as follows: Input setting: The carbon deposit amount in the power supply room is classified. If the carbon monoxide concentration in the power supply room exceeds the preset carbon concentration threshold, the first input is set to 0, otherwise it is set to 1. If the bearing wear assessment result of the standby generator is severe wear, the second input is set to 0, otherwise it is set to 1. Determine the power supply status: When both input states are 1, it is determined that the power supply status of the backup generator is good; when there is a 0 in the two input states, it is determined that the power supply status of the backup generator is abnormal.

[0013] In a preferred embodiment, the alarm rules are set as follows: Rule 1: When the power supply rate of the current-carrying conductor is marked as safe and the status signal of the backup generator is normal, the power supply continues; Rule 2: When the power supply rate of the current-carrying conductor is marked as abnormal and the status signal of the standby generator is normal, an alarm is issued; Rule 3: When the status signal of the backup generator is abnormal, power is cut off.

[0014] The technical effects and advantages of the plant electrical equipment control system based on the Internet of Things of the present invention are as follows: The present invention detects the power supply temperature of the standby generator in real time, and determines whether the standby generator has abnormal heating by comparing it with the normal stable range. If it is not abnormal heating, the vibration frequency of the standby generator bearing and the sound frequency under the power supply state are collected. While making an initial abnormal judgment on the standby generator, data is collected when it is not abnormally heated to reduce the collection cost. The wear of the standby generator bearing is evaluated through the changes in the vibration frequency and sound frequency of the standby generator, and the carbon deposit amount in the power supply room is detected. The power supply state of the standby generator is determined based on the comprehensive evaluation results of the bearing wear of the standby generator and the carbon deposit amount in the power supply room. The power supply rate of the current-carrying conductor is detected in real time, and power supply or power-off alarm is selected according to the power supply state of the standby generator and the power supply rate of the current-carrying conductor, thereby ensuring the power supply safety of the standby generator and providing sufficient preparation time for generator maintenance. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 This is a flow chart of the plant electrical equipment control system based on the Internet of Things of the present invention; Figure 2 This is a schematic diagram of the factory electrical equipment control system based on the Internet of Things of the present invention. DETAILED DESCRIPTION

[0016] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0017] The present invention detects the power supply temperature of the standby generator in real time, and determines whether the standby generator has abnormal heating by comparing it with the normal stable range. If it is not abnormal heating, the vibration frequency of the standby generator bearing and the sound frequency under the power supply state are collected, and the wear of the standby generator bearing is evaluated through the changes in the vibration frequency and sound frequency of the standby generator. The carbon deposit amount in the power supply room is detected, and the power supply state of the standby generator is determined based on the comprehensive evaluation results of the bearing wear of the standby generator and the carbon deposit amount in the power supply room. The power supply rate of the current-carrying conductor is detected in real time, and power supply or power-off alarm is selected according to the power supply state of the standby generator and the power supply rate of the current-carrying conductor.

[0018] Example 1: A plant electrical equipment control system based on the Internet of Things, such as Figure 2 As shown, it includes a data acquisition module, an abnormality judgment module, a power supply evaluation module and a response alarm module, and the signal connections between the modules are; The functions of each module are as follows: The data acquisition module is used to detect the power supply temperature of the standby generator in real time and transmit it to the abnormality judgment module. When receiving the normal power supply temperature signal, it detects the amount of carbon deposits in the power supply room and collects the vibration frequency of the standby generator bearing and the sound frequency under the power supply state and transmits them together to the power supply evaluation module. After receiving the status signal sent by the power supply evaluation module, it continuously detects the power supply rate of the current-carrying conductor and transmits the detection data to the response alarm module; The abnormality judgment module is used to receive the power supply temperature of the standby generator and compare it with the normal power supply temperature range of the standby generator in the monitoring system database to determine whether the power supply temperature of the standby generator is abnormal. According to the judgment result, an abnormal power supply temperature signal or a normal power supply temperature signal is set, and the normal power supply temperature signal is transmitted back to the data acquisition module, and the abnormal power supply temperature signal is transmitted to the response alarm module; The power supply assessment module is used to receive the amount of carbon deposits in the power supply room, the vibration frequency of the standby generator bearing, and the sound frequency under the power supply state. The module uses a random forest algorithm to assess the wear of the standby generator bearing based on the vibration frequency of the standby generator and the frequency of sound changes under the power supply state. The power supply state of the standby generator is determined based on the comprehensive assessment results of the bearing wear of the standby generator and the amount of carbon deposits in the power supply room. The status signal is set to be transmitted to the data acquisition module and the response alarm module according to the power supply state of the standby generator. The response alarm module is used to receive the power supply rate detection result and status signal of the current-carrying conductor and set the alarm rules, and perform power supply, alarm or power off response processing according to the alarm rules.

[0019] It should be noted that the power supply temperature of the standby generator directly reflects whether there is any abnormality in the power supply process of the standby generator. When the power supply temperature exceeds the normal power supply temperature range of the generator, the power supply process is abnormal. The vibration frequency of the standby generator bearing and the sound frequency under the power supply state can reflect the degree of wear of the standby generator bearing. The higher the vibration frequency or the greater the change in the sound frequency under the power supply state, the greater the degree of wear of the standby generator bearing, the worse the power supply state of the standby generator, the more carbon deposits in the power supply chamber, the smaller the actual volume of the cylinder, the increased compression ratio, and the easier it is to damage the internal parts of the standby generator. The current-carrying conductor is the conductive material that transmits the current supplied by the standby generator to the electrical equipment.

[0020] When detecting the power supply temperature of the standby generator, the data acquisition module monitors the power supply temperature in real time by connecting to the generator set brush infrared thermal imaging online monitoring system, and transmits the data to the abnormality judgment module in real time. When detecting the amount of carbon deposits in the power supply room, the data acquisition module detects the carbon monoxide concentration in the power supply room through a gas analyzer and transmits it to the power supply evaluation module.

[0021] The vibration frequency of the generator bearing is the vibration speed of the engine. The faster the vibration frequency of the generator, the greater the wear of the standby generator. The sound change frequency in the power supply state is the degree of change of the sound frequency generated by the standby generator when supplying power. The faster the sound change frequency, the greater the wear of the standby engine.

[0022] Before collecting the vibration frequency of the standby generator bearing, the data acquisition module selects a period of time as the detection time, divides the detection time into N equal parts, and takes each time as a time group. The vibration frequency of the standby generator bearing in each time group is collected by the vibration spectrum analyzer and the average value is taken as the bearing vibration frequency of the corresponding time group; when collecting the sound frequency under the power supply state, the data acquisition module receives the sound frequency obtained by the FFT analyzer in each time group, selects the maximum and minimum values ​​of the sound frequency in the corresponding time group, and takes the difference between the maximum and minimum values ​​of the sound frequency in each time group to obtain the sound change frequency of the corresponding time group, and transmits the bearing vibration frequency and sound change frequency of each time group to the power supply evaluation module.

[0023] After receiving the status signal sent by the power supply evaluation module, the data acquisition module identifies the status signal. When the status signal is an abnormal status signal, the power supply rate of the current-carrying conductor is not detected, thereby reducing the detection cost; when the status signal is a good status signal, the line switch connected to the current sensor is opened, and the current-carrying conductor is continuously detected through the current sensor and the detection data is transmitted to the response alarm module.

[0024] It should be noted that the infrared thermal imaging online monitoring system for generator brushes is a coefficient used to monitor the status of motor brushes in real time. It uses infrared thermal imaging technology to monitor the temperature of brushes and related components in real time, and can be used to monitor the power supply temperature of the standby generator in real time. The gas analyzer is a device used to detect and analyze gas composition, which can be used to detect the carbon monoxide concentration in the power supply room. The vibration spectrometer is an instrument used to measure and analyze the vibration of mechanical systems. It can capture and process vibration signals to generate spectrum diagrams, and can be used to collect the vibration frequency of the standby generator bearings. The FFT analyzer is an instrument used for frequency analysis, mainly used for vibration analysis and signal processing. It can digitize the detected sound frequency. The time interval of the detection time and the number of time groups can be set by yourself, which will not be elaborated here.

[0025] The abnormality judgment module accesses the monitoring system database to determine the normal power supply temperature range of the standby generator, compares the power supply temperature of the standby generator input through the data acquisition module with the normal power supply temperature range of the standby generator to set the power supply temperature signal. When the power supply temperature of the standby generator is within the normal power supply temperature range of the standby generator, it is judged that the power supply of the standby generator is normal, and the power supply temperature signal is set to the normal power supply temperature signal; when the power supply temperature of the standby generator is outside the normal power supply temperature range of the standby generator, it is judged that the power supply of the standby generator is abnormal, and the power supply temperature signal is set to the abnormal power supply temperature signal.

[0026] The abnormality judgment module transmits the normal power supply temperature signal back to the data acquisition module. When the data acquisition module receives the normal power supply temperature signal, it detects the amount of carbon deposits in the power supply room and collects the vibration frequency of the standby generator bearing and the sound frequency under the power supply state. If the normal power supply temperature signal is not received, no data collection is performed, thereby reducing the collection cost.

[0027] The abnormality judgment module transmits the abnormal power supply temperature signal to the response alarm module, and the response alarm module cuts off the power and issues an alarm after successfully identifying the incoming signal.

[0028] It should be noted that the monitoring system database is used to monitor the performance of the backup generator. It can record temperature data in real time and store the normal power supply temperature range of the backup generator for call analysis.

[0029] After receiving the bearing vibration frequency and sound change frequency of each time group, the power supply assessment module uses the random forest algorithm to assess the wear of the standby generator bearings. The specific steps are as follows: Feature confirmation: Bearing vibration frequency and sound change frequency are used as input features, and wear assessment is defined as output feature; Data preprocessing: Merge each time group as one data into the input feature dataset; Data splitting: Divide the input feature dataset into a training set and a test set. For example, 80% of the data in the input feature dataset is used as the training set, and 20% of the data in the input feature dataset is used as the test set. Data processing: Randomly extract multiple data points from the training set, and use each of these data points as a training sample. Randomly extract multiple data points from the test set, and use each of these data points as a test sample. It should be noted that each data point is recorded and replaced after extraction.

[0030] Construct a decision tree: For each training sample and test sample, construct a decision tree. At each node of the tree, randomly select one or more input features from the training sample or test sample to store. That is, at each node, randomly store the bearing vibration frequency or sound change frequency, or store both input features. Establishing a feature selection threshold: Count the number of occurrences of each input feature in all decision trees in the training sample, and use the ratio of the number of occurrences of the input feature to the number of occurrences of all input features as the weight of the corresponding input feature. Normalize the input features in each training sample and take the weighted sum as the feature selection threshold. Screening feature selection threshold: Count the number of occurrences of each input feature in all decision trees in the test sample and use the ratio of the number of occurrences of the input feature to the number of occurrences of all input features as the weight of the corresponding input feature. Normalize the input features in each test sample and then perform a weighted sum as the feature comparison threshold. Subtract the feature comparison threshold from the feature selection threshold and compare it with the preset screening coefficient. When the difference result is lower than the screening coefficient, retain the feature selection threshold; when the difference result exceeds the screening coefficient, rebuild the decision tree and randomly store the bearing vibration frequency or sound change frequency or both input features in each node. It should be explained that the closer the feature selection threshold is to the feature comparison threshold, the higher the accuracy of the set feature selection threshold in classifying the output features.

[0031] Wear assessment: The received bearing vibration frequency and sound change frequency are normalized and then summed to take the average value as the bearing wear coefficient of the standby generator. The wear coefficient of the standby generator is compared with the feature selection threshold. When the wear coefficient of the standby generator exceeds the feature selection threshold, the standby generator bearing is judged to be severely worn; when the wear coefficient of the standby generator is lower than the feature selection threshold, the standby generator bearing is judged to be slightly worn.

[0032] It should be noted that the split ratio of the training set and the test set in the random forest algorithm can be set by yourself, and the formulation of the feature selection threshold is not unique and will not be analyzed here.

[0033] The power supply assessment module determines the power supply status of the standby generator based on the bearing wear assessment results of the standby generator and the amount of carbon deposits in the power supply room. The specific steps are as follows: Input setting: The carbon deposit amount in the power supply room is classified. If the carbon monoxide concentration in the power supply room exceeds the preset carbon concentration threshold, the first input is set to 0, otherwise it is set to 1. If the bearing wear assessment result of the standby generator is severe wear, the second input is set to 0, otherwise it is set to 1. Determine the power supply status: When both input states are 1, the power supply status of the backup generator is judged to be good; when either input state is 0, the power supply status of the backup generator is judged to be abnormal; When the judgment result is that the backup generator is good, the power supply evaluation module sets the status signal to good; when the judgment result is that the backup generator is abnormal, the power supply evaluation module sets the status signal to abnormal, and transmits the status signal to the data acquisition module and the response alarm module. After receiving the status signal, the data acquisition module continuously detects the power supply rate of the current-carrying conductor and transmits the detection data to the response alarm module.

[0034] After receiving the power supply rate detection result of the current-carrying conductor, the response alarm module compares it with the current-carrying conductor power supply rate safety range in the monitoring system database. When the power supply rate detection result of the current-carrying conductor is within the current-carrying conductor power supply rate safety range, the power supply rate is marked as safe, otherwise it is marked as abnormal.

[0035] The response alarm module receives the power supply rate of the current-carrying conductor and the status signal of the standby generator and sets the alarm rules as follows: Rule 1: When the power supply rate of the current-carrying conductor is marked as safe and the status signal of the backup generator is normal, the power supply continues; Rule 2: When the power supply rate of the current-carrying conductor is marked as abnormal and the status signal of the standby generator is normal, an alarm is issued; Rule 3: When the status signal of the backup generator is abnormal, power is cut off.

[0036] It should be noted that there are many ways to handle the alarm, and you can choose to make a sound or send an alarm message to the person in charge to achieve the alarm effect.

[0037] The above embodiments may be implemented in whole or in part through software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments may be implemented in whole or in part in the form of a computer program product.

[0038] Those skilled in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application of the technical solution and the invention constraints. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0039] In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0040] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

[0041] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. The plant electrical equipment control system based on the Internet of Things is characterized by: include: Data acquisition module, abnormality judgment module, power supply assessment module and response alarm module, and signal connections between each module; The data acquisition module is used to detect the power supply temperature of the standby generator in real time and transmit it to the abnormality judgment module. When receiving the normal power supply temperature signal, it detects the amount of carbon deposits in the power supply room and collects the vibration frequency of the standby generator bearing and the sound frequency under the power supply state and transmits them together to the power supply evaluation module. After receiving the status signal sent by the power supply evaluation module, it continuously detects the power supply rate of the current-carrying conductor and transmits the detection data to the response alarm module; The abnormality judgment module is used to receive the power supply temperature of the standby generator and compare it with the normal power supply temperature range of the standby generator in the monitoring system database to determine whether the power supply temperature of the standby generator is abnormal. According to the judgment result, an abnormal power supply temperature signal or a normal power supply temperature signal is set, and the normal power supply temperature signal is transmitted back to the data acquisition module, and the abnormal power supply temperature signal is transmitted to the response alarm module; The power supply assessment module is used to receive the amount of carbon deposits in the power supply room, the vibration frequency of the standby generator bearing, and the sound frequency under the power supply state. The module uses a random forest algorithm to assess the wear of the standby generator bearing based on the vibration frequency of the standby generator and the frequency of sound changes under the power supply state. The power supply state of the standby generator is determined based on the comprehensive assessment results of the bearing wear of the standby generator and the amount of carbon deposits in the power supply room. The status signal is set to be transmitted to the data acquisition module and the response alarm module according to the power supply state of the standby generator. The response alarm module is used to receive the power supply rate detection result and status signal of the current-carrying conductor and set the alarm rules, and perform power supply, alarm or power off response processing according to the alarm rules.

2. The plant electrical equipment control system based on the Internet of Things according to claim 1, characterized in that: The data acquisition module determines the amount of carbon deposits in the power supply room by detecting the carbon monoxide concentration in the power supply room; The data acquisition module selects a period of time as the detection time before collecting the vibration frequency of the standby generator bearing, divides the detection time into N equal parts, and regards each time as a time group. The vibration frequency of the standby generator bearing in each time group is collected by the vibration spectrum analyzer, and the average value is taken as the bearing vibration frequency of the corresponding time group; When the data acquisition module collects the sound frequency in the power supply state, it detects the sound frequency obtained in each time group, selects the maximum and minimum sound frequencies in the corresponding time group, takes the difference between the maximum and minimum sound frequencies in each time group to obtain the sound change frequency of the corresponding time group, and transmits the bearing vibration frequency and sound change frequency of each time group to the power supply evaluation module.

3. The plant electrical equipment control system based on the Internet of Things according to claim 1 is characterized in that: The abnormality judgment module accesses the monitoring system database to determine the normal power supply temperature range of the standby generator, compares the power supply temperature of the standby generator input through the data acquisition module with the normal power supply temperature range of the standby generator to set the power supply temperature signal. When the power supply temperature of the standby generator is within the normal power supply temperature range of the standby generator, it is judged that the power supply of the standby generator is normal, and the power supply temperature signal is set to the normal power supply temperature signal; when the power supply temperature of the standby generator is outside the normal power supply temperature range of the standby generator, it is judged that the power supply of the standby generator is abnormal, and the power supply temperature signal is set to the abnormal power supply temperature signal.

4. The plant electrical equipment control system based on the Internet of Things according to claim 3 is characterized in that: The abnormality judgment module transmits the normal power supply temperature signal back to the data acquisition module. When the data acquisition module receives the normal power supply temperature signal, it detects the amount of carbon deposits in the power supply room and collects the vibration frequency of the standby generator bearing and the sound frequency under the power supply state. If the normal power supply temperature signal is not received, no data collection is performed.

5. The plant electrical equipment control system based on the Internet of Things according to claim 2, characterized in that: After receiving the bearing vibration frequency and sound change frequency of each time group, the power supply assessment module uses the random forest algorithm to assess the wear of the standby generator bearings. The specific steps are as follows: Feature confirmation: Bearing vibration frequency and sound change frequency are used as input features, and wear assessment is defined as output feature; Data preprocessing: Merge each time group as one data into the input feature dataset; Data segmentation: Split the input feature dataset into training and test sets; Data processing: randomly extract multiple data from the training set and use each extracted data as a training sample; Randomly extract multiple data from the test set and use each extracted data as a test sample; Construct a decision tree: For each training sample and test sample, construct a decision tree. At each node of the tree, randomly select one or more input features from the training sample or test sample to store; Establishing a feature selection threshold: Count the number of occurrences of each input feature in all decision trees in the training sample, and use the ratio of the number of occurrences of the input feature to the number of occurrences of all input features as the weight of the corresponding input feature. Normalize the input features in each training sample and take the weighted sum as the feature selection threshold. Screening feature selection threshold: Use test samples to set feature comparison thresholds, and screen feature selection thresholds based on the feature comparison thresholds; Wear assessment: The received bearing vibration frequency and sound change frequency are normalized and then summed to take the average value as the bearing wear coefficient of the standby generator. The wear coefficient of the standby generator is compared with the feature selection threshold for wear assessment.

6. The plant electrical equipment control system based on the Internet of Things according to claim 5 is characterized in that: The specific steps for screening feature selection thresholds are as follows: The number of occurrences of each input feature in all decision trees in the test sample is counted, and the ratio of the number of occurrences of the input feature to the number of occurrences of all input features is used as the weight of the corresponding input feature. The input features in each test sample are normalized and then weighted summed as the feature comparison threshold. The feature comparison threshold is subtracted from the feature selection threshold and then compared with the preset screening coefficient. When the difference result is lower than the screening coefficient, the feature selection threshold is retained; when the difference result exceeds the screening coefficient, the decision tree is reconstructed, and the bearing vibration frequency or sound change frequency or both input features are randomly stored in each node.

7. The plant electrical equipment control system based on the Internet of Things according to claim 5, characterized in that: When the wear coefficient of the standby generator exceeds the feature selection threshold, the standby generator bearing is judged to be severely worn; when the wear coefficient of the standby generator is lower than the feature selection threshold, the standby generator bearing is judged to be slightly worn.

8. The plant electrical equipment control system based on the Internet of Things according to claim 7 is characterized in that: The specific steps for determining the power supply status of the standby generator based on the bearing wear assessment results of the standby generator and the amount of carbon deposits in the power supply room are as follows: Input setting: The carbon deposit amount in the power supply room is classified. If the carbon monoxide concentration in the power supply room exceeds the preset carbon concentration threshold, the first input is set to 0, otherwise it is set to 1. If the bearing wear assessment result of the standby generator is severe wear, the second input is set to 0, otherwise it is set to 1. Determine the power supply status: When both input states are 1, it is determined that the power supply status of the backup generator is good; when there is a 0 in the two input states, it is determined that the power supply status of the backup generator is abnormal.

9. The plant electrical equipment control system based on the Internet of Things according to claim 8, characterized in that: The alarm rules are set as follows: Rule 1: When the power supply rate of the current-carrying conductor is marked as safe and the status signal of the backup generator is normal, the power supply continues; Rule 2: When the power supply rate of the current-carrying conductor is marked as abnormal and the status signal of the standby generator is normal, an alarm is issued; Rule 3: When the status signal of the backup generator is abnormal, power is cut off.

Images