Safe operation monitoring and alarming system and device of new energy microgrid and storage medium

Abstract

The invention provides a safe operation monitoring alarm system and device of a new energy microgrid and a storage medium, the safe operation monitoring alarm system comprises a data acquisition module, a data processing and analysis module and an alarm module, and the data acquisition module equipped with various sensors monitors various electric power parameters of the new energy microgrid in real time; the data processing and analysis module is used for providing accurate data for the data processing and analysis module, the fault diagnosis unit configured for the data processing and analysis module performs feature extraction on the preprocessed data and inputs an artificial neural network model for training, and compared with a traditional mode that fault diagnosis is performed through expert experience, the fault diagnosis efficiency is improved. The artificial neural network model can continuously optimize and improve the fault identification capability, quickly and accurately determine the fault type and the fault probability according to the activation value of the output layer, and send the fault information to the alarm module, so that the new energy microgrid operation fault can be timely and effectively alarmed, and highly credible guidance is provided for maintenance personnel.

Description

Technical Field

[0001] The present invention relates to the field of microgrid safety technology, and in particular to a new energy microgrid safety operation monitoring and alarm system, device and storage medium. Background Art

[0002] With the continuous development of new energy technology, new energy microgrids have attracted widespread attention as an efficient and environmentally friendly way of energy utilization. New energy microgrids are mainly composed of renewable energy power generation units, energy storage units, load units and control systems, and have outstanding characteristics such as distributed, autonomous and scalable. However, in the operation of new energy microgrids, there are also many types of faults, such as voltage anomalies, current anomalies, power anomalies, etc., which seriously affect the stability and safety of the system. Therefore, how to effectively monitor the operation status of new energy microgrids and timely discover and handle faults has become an urgent problem to be solved. The existing new energy microgrid monitoring system usually has modules such as data acquisition, data processing and analysis, and alarm. However, the fault diagnosis method configured by the existing monitoring system often relies on expert experience and is difficult to adapt to the complex microgrid operation environment; at the same time, the existing empirical prediction model is difficult to accurately predict the occurrence of faults, resulting in the inability of maintenance personnel to timely discover faults and take countermeasures during operation and maintenance. Summary of the invention

[0003] Purpose of the invention: The purpose of the present invention is to provide a safe operation monitoring and alarm system, device and storage medium for a new energy microgrid that can quickly and accurately identify faults.

[0004] Technical solution: A safe operation monitoring and alarm system for a new energy microgrid includes a data acquisition module, a data processing and analysis module and an alarm module. The data acquisition module is connected to the data processing and analysis module, and the alarm module is connected to the data processing and analysis module. The data acquisition module is used to collect data on the operation of the new energy microgrid and transmit it to the data processing and analysis module. The data processing and analysis module includes a data preprocessing unit, a data storage unit, a data analysis unit and a fault diagnosis unit. The data storage unit is used to store data preprocessed by the data preprocessing unit and provide a data access interface for the data analysis unit. The data analysis unit is used to perform statistical analysis on the preprocessed data to obtain data distribution results. The fault diagnosis unit is used to use an artificial neural network model to perform fault detection and output diagnosis results on the preprocessed data. The alarm unit is used to receive the diagnosis results of the data processing and analysis module and issue an alarm.

[0005] Preferably, the safe operation monitoring and alarm system also includes a user interface module and a log management module. The user interface module is connected to the data acquisition module, the data processing and analysis module, the alarm module and the log management module, and is used to display the information received from the data acquisition module, the data processing and analysis module and the alarm module, and provide a user operation interface; the log management module is used to receive log information from the data acquisition module, the data processing and analysis module, the alarm module and the user interface module, and to record, store, query, analyze and back up the log information.

[0006] Specifically, the data acquisition module includes a voltage sensor, a current sensor, a power sensor and a frequency sensor.

[0007] Specifically, the data preprocessing unit is used to calculate the standard score of the data of the new energy microgrid operation.

[0008] Specifically, the data analysis unit is used to calculate the mean, median and standard deviation of the preprocessed data.

[0009] Specifically, the fault diagnosis unit includes a feature extraction subunit and a model building subunit. The feature extraction subunit is used to extract the time domain characteristics and frequency domain characteristics of the data of the new energy microgrid operation; the model building subunit is used to train the time domain and frequency domain characteristics of the data of the new energy microgrid operation using an artificial neural network model to obtain output results.

[0010] Specifically, the artificial neural network model includes an input layer, a hidden layer and an output layer. The number of neurons in the input layer is the same as the total number of time domain features and frequency domain features, and the number of neurons in the output layer is the same as the number of fault types.

[0011] Specifically, the training of the artificial neural network model includes the following steps:

[0012] (1) Initialize model parameters: randomly initialize weights and biases;

[0013] (2) Forward propagation: Input the parameters of time domain features and frequency domain features, calculate the activation values ​​of the hidden layer and output layer, and the forward propagation formula is:

[0014]

[0015] Where: is the activation value of the jth neuron in the lth layer, is the weight from the i-th neuron in the l-1th layer to the j-th neuron in the lth layer, is the bias of the jth neuron in the lth layer, σ is the activation function, n l-1 is the number of neurons in the l-1th layer;

[0016] (3) Calculate the loss function: Calculate the difference between the activation value of the output layer and the actual fault type. The loss function formula is:

[0017]

[0018] Where: is the loss function, is the independent code of the actual fault type of the ith sample, represents the activation value of the output layer of the i-th sample, m is the number of samples, n out is the number of neurons in the output layer;

[0019] (4) Back propagation: Calculate the gradient of the loss function with respect to weights and biases, and update the weights and biases. The back propagation formula is:

[0020]

[0021] Where: is the loss function over weights The gradient of is the error of the jth neuron in the lth layer, is the activation value of the jth neuron in the l-1th layer.

[0022] The present invention also provides a new energy microgrid safe operation monitoring and alarm device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the functions of the new energy microgrid safe operation monitoring and alarm system are realized.

[0023] The present invention also provides a readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the functions of the safe operation monitoring and alarm system of the new energy microgrid are realized.

[0024] Beneficial effect: Compared with the prior art, the significant effect of the present invention is: the present invention monitors various power parameters of the new energy microgrid in real time through a data acquisition module equipped with a variety of sensors, and provides high-precision real-time data for the data processing and analysis module. The data processing and analysis module is configured with multiple functional units, among which the fault diagnosis unit extracts features from the preprocessed data and inputs the data into the artificial neural network model for training. Compared with the traditional method of fault diagnosis through expert experience, the artificial neural network model can continuously optimize and improve the fault recognition ability, quickly and accurately determine the fault type and fault probability according to the activation value of the output layer, and promptly and effectively alarm the new energy microgrid operation failure, providing highly reliable guidance for maintenance personnel. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1This is an architecture diagram of the safe operation monitoring and alarm system of the new energy microgrid according to Example 1 of the present invention. DETAILED DESCRIPTION

[0026] The present invention is further described below in conjunction with the accompanying drawings.

[0027] Example 1

[0028] See also Figure 1 As shown, this embodiment provides a new energy microgrid safety operation monitoring and alarm system, including a data acquisition module, a data processing and analysis module, an alarm module, a user interface module and a log management module, the data acquisition module is connected to the data processing and analysis module, and the alarm module is connected to the data processing and analysis module; the data acquisition module is used to collect data on the operation of the new energy microgrid and transmit it to the data processing and analysis module; the data processing and analysis module includes a data preprocessing unit, a data storage unit, a data analysis unit and a fault diagnosis unit, the data storage unit is used to store the data preprocessed by the data preprocessing unit, and provide a data access interface for the data analysis unit, the data analysis unit is used to perform statistical analysis on the preprocessed data to obtain data distribution results, and the fault diagnosis unit is used to use an artificial neural network model to perform fault detection and output diagnosis results on the preprocessed data; the alarm unit is used to receive the diagnosis result of the data processing and analysis module and issue an alarm. The user interface module is connected to the data acquisition module, data processing and analysis module, alarm module and log management module, and is used to display the information received from the data acquisition module, data processing and analysis module and alarm module, and provide a user operation interface; the log management module is used to receive log information from the data acquisition module, data processing and analysis module, alarm module and user interface module, and to record, store, query, analyze and back up the log information.

[0029] In this embodiment, the data acquisition module includes a voltage sensor, a current sensor, a power sensor and a frequency sensor, and the above sensors all have accurate measurement capabilities to ensure the stability of the microgrid operation.

[0030] In a specific implementation scenario, the voltage sensor model is LEMLTS6-NP, which has a range of 0-1000V and a reading accuracy of ±0.5%, a response time of no more than 1ms, an operating temperature range of -40°C to +85°C, and provides an output of ±5V or 4-20mA; the current sensor model is LEMLA55-P, which has a range of 0-200A and a reading accuracy of ±1%, a response time of no more than 5μs, an operating temperature range of -40°C to +85°C, and supports an output of ±5V or 4-20mA; the power sensor model is LEMHX50, which has a range of 0-50kW and a reading accuracy of ±1%. The frequency sensor model is OMRONE8Y, which has a measurement range of 0.5Hz to 10kHz and a reading accuracy of ±0.05%, a response time of no more than 1ms, an operating temperature range of -25℃ to +85℃, and supports NPN or PNP switch output; the above sensors convert analog signals into digital signals through an analog-to-digital converter (ADC) and transmit them to the data processing and analysis module for processing; at the same time, the sensors need to be calibrated regularly to ensure the reliability of the data.

[0031] In this embodiment, the data preprocessing unit converts the received raw data of the operation of the new energy microgrid into a standard score (z-score), and the specific steps include:

[0032] (1) For each data type in the original data of the new energy microgrid operation, calculate its mean and standard deviation;

[0033] (2) Apply the following formula to transform each data type in the original data of the new energy microgrid operation:

[0034]

[0035] Where: x std is the value after data transformation, x is the original data value, Mean is the mean, and std is the standard deviation. After the above transformation, the mean of each data type is 0, the standard deviation is 1, and the distribution of the data set is similar to the standard normal distribution.

[0036] In this embodiment, the data analysis unit retrieves the preprocessed data from the data storage unit, and performs statistical analysis to calculate the mean, median, and standard deviation of each type of data to obtain the distribution characteristics of the data.

[0037] In this embodiment, the fault diagnosis unit includes a feature extraction subunit and a model building subunit. The feature extraction subunit is used to extract the time domain characteristics and frequency domain characteristics of the data of the new energy microgrid operation; the model building subunit uses an artificial neural network model to train the time domain and frequency domain characteristics of the data of the new energy microgrid operation to obtain output results.

[0038] In this embodiment, the artificial neural network model includes an input layer, a hidden layer and an output layer. The number of neurons in the input layer is the same as the total number of time domain features and frequency domain features. The number of hidden layers and the neuron data of each hidden layer can be adaptively adjusted according to the actual needs of the microgrid operation. The number of neurons in the output layer is the same as the number of fault types.

[0039] In this embodiment, the training of the artificial neural network model includes the following steps:

[0040] (1) Initialize model parameters: randomly initialize weights and biases;

[0041] (2) Forward propagation: Input the parameters of time domain features and frequency domain features, calculate the activation values ​​of the hidden layer and output layer, and the forward propagation formula is:

[0042]

[0043] Where: is the activation value of the jth neuron in the lth layer, is the weight from the i-th neuron in the l-1th layer to the j-th neuron in the lth layer, is the bias of the jth neuron in the lth layer, σ is the activation function, n l-1 is the number of neurons in the l-1th layer;

[0044] (3) Calculate the loss function: Calculate the difference between the activation value of the output layer and the actual fault type. The loss function formula is:

[0045]

[0046] Where: is the loss function, is the independent code of the actual fault type of the ith sample, represents the activation value of the output layer of the i-th sample, m is the number of samples, n out is the number of neurons in the output layer;

[0047] (4) Back propagation: Calculate the gradient of the loss function with respect to weights and biases, and update the weights and biases. The back propagation formula is:

[0048]

[0049] Where: is the loss function over weights The gradient of is the error of the jth neuron in the lth layer, is the activation value of the jth neuron in the l-1th layer.

[0050] After setting rounds of training, the artificial neural network model is used for fault diagnosis. The characteristic parameters of the data of the new energy microgrid operation to be tested are input, the activation values ​​of the hidden layer and the output layer are calculated, and the fault type and fault probability are determined according to the activation value of the output layer.

[0051] In a specific application scenario, the fault types include:

[0052] (1) Battery energy storage system failure: unbalanced charge and discharge, battery overheating, internal battery short circuit, and battery capacity attenuation;

[0053] (2) Solar photovoltaic system failures: photovoltaic panel shadowing, component aging, inverter failure, and system efficiency reduction;

[0054] (3) Wind power generation system failure: blade damage, generator bearing wear, converter failure, control system failure;

[0055] (4) Microgrid on-grid and off-grid switching failures: on-grid / off-grid switching failures, grid synchronization problems, and grid voltage fluctuation response failures;

[0056] (5) Microgrid protection device failure: overcurrent protection malfunction, overvoltage protection failure, and protection device communication interruption.

[0057] For the above fault types, the design of the model building subunit is as follows:

[0058] Input layer: The number of neurons in the input layer is the same as the total number of time domain features and frequency domain features. The feature parameters include the real-time values ​​of sensors such as current, voltage, frequency, power and their rates of change.

[0059] Hidden layer: The number of hidden layers and the number of neurons in each hidden layer need to be selected according to the specific monitoring problem and data complexity, and the optimal hidden layer structure should be selected through methods such as cross-validation.

[0060] Output layer: The number of neurons in the output layer is the same as the number of fault types. In this application scenario, there should be 5 neurons corresponding to the above 5 main fault types, and they correspond to the fault types one by one. For each fault type, it can be further subdivided into subtypes and represented by multiple output neurons, that is, it can be further subdivided into 18 neurons.

[0061] In this embodiment, the alarm module is triggered after the data processing and analysis module detects a fault. According to the type and severity of the fault, the alarm information is sent to the user interface module for display through a preset alarm method, and the alarm event message is sent to the log management module. The alarm module can also directly alert on-site personnel by configuring sound, light and other alarm equipment.

[0062] In this embodiment, the user interface module includes real-time data display, historical data query, alarm information display and system setting functions; the real-time data display area displays the voltage, current, power and frequency parameters of the current new energy microgrid; historical data query allows the user to retrieve data records within a period of time in the past; the alarm information display area updates the alarm status and fault information in real time; the system settings allow the user to configure the alarm threshold and alarm mode parameters; the user interface module enables users to easily monitor the status of the new energy microgrid, adjust system settings and receive alarm notifications through a graphical interface and interactive controls.

[0063] In this embodiment, the safe operation monitoring and alarm system of the new energy microgrid is configured with multiple communication protocols and is adapted to multiple communication interfaces. The communication protocols include Modbus, TCP / IP, and CAN, and the data transmission rates are 9600bps and 19200bps; the communication interfaces include RS-485, Ethernet, and wireless.

[0064] Example 2

[0065] This embodiment provides a new energy microgrid safe operation monitoring and alarm device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the functions of the new energy microgrid safe operation monitoring and alarm system described in Embodiment 1 are implemented.

[0066] Example 3

[0067] This embodiment provides a readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the functions of the safe operation monitoring and alarm system of the new energy microgrid described in Example 1 are implemented.

Claims

1. A new energy microgrid safety operation monitoring and alarm system, characterized in that: It includes a data acquisition module, a data processing and analysis module and an alarm module, the data acquisition module is connected to the data processing and analysis module, and the alarm module is connected to the data processing and analysis module; the data acquisition module is used to collect data on the operation of the new energy microgrid and transmit it to the data processing and analysis module; the data processing and analysis module includes a data preprocessing unit, a data storage unit, a data analysis unit and a fault diagnosis unit, the data storage unit is used to store the data preprocessed by the data preprocessing unit, and provide a data access interface for the data analysis unit, the data analysis unit is used to perform statistical analysis on the preprocessed data to obtain data distribution results, the fault diagnosis unit is used to use an artificial neural network model to perform fault detection and output diagnosis results on the preprocessed data; the alarm unit is used to receive the diagnosis results of the data processing and analysis module and issue an alarm.

2. The safe operation monitoring and alarm system according to claim 1 is characterized in that: The safe operation monitoring and alarm system also includes a user interface module and a log management module. The user interface module is connected to the data acquisition module, the data processing and analysis module, the alarm module and the log management module, and is used to display the information received from the data acquisition module, the data processing and analysis module and the alarm module, and provide a user operation interface; the log management module is used to receive log information from the data acquisition module, the data processing and analysis module, the alarm module and the user interface module, and to record, store, query, analyze and back up the log information.

3. The safe operation monitoring and alarm system according to claim 1 is characterized in that: The data acquisition module includes a voltage sensor, a current sensor, a power sensor and a frequency sensor.

4. The safe operation monitoring and alarm system according to claim 1 is characterized in that: The data preprocessing unit is used to calculate the standard score of the data of the new energy microgrid operation.

5. The safe operation monitoring and alarm system according to claim 1 is characterized in that: The data analysis unit is used to calculate the mean, median and standard deviation of the preprocessed data.

6. The safe operation monitoring and alarm system according to claim 1 is characterized in that: The fault diagnosis unit includes a feature extraction subunit and a model building subunit, wherein the feature extraction subunit is used to extract time domain features and frequency domain features of data of the operation of the new energy microgrid; The model building subunit is used to train the time domain and frequency domain characteristics of the data of the new energy microgrid operation using an artificial neural network model to obtain an output result.

7. The safe operation monitoring and alarm system according to claim 6 is characterized in that: The artificial neural network model comprises an input layer, a hidden layer and an output layer. The number of neurons in the input layer is the same as the total number of time domain features and frequency domain features, and the number of neurons in the output layer is the same as the number of fault types.

8. The safe operation monitoring and alarm system according to claim 7 is characterized in that: The training of the artificial neural network model comprises the following steps: (1) Initialize model parameters: randomly initialize weights and biases; (2) Forward propagation: Input the parameters of time domain features and frequency domain features, calculate the activation values ​​of the hidden layer and output layer, and the forward propagation formula is: Where: is the activation value of the jth neuron in the lth layer, is the weight from the i-th neuron in the l-1th layer to the j-th neuron in the lth layer, is the bias of the jth neuron in the lth layer, σ is the activation function, n l-1 is the number of neurons in the l-1th layer; (3) Calculate the loss function: Calculate the difference between the activation value of the output layer and the actual fault type. The loss function formula is: Where: is the loss function, is the independent code of the actual fault type of the ith sample, represents the activation value of the output layer of the i-th sample, m is the number of samples, n out is the number of neurons in the output layer; (4) Back propagation: Calculate the gradient of the loss function with respect to weights and biases, and update the weights and biases. The back propagation formula is: Where: is the loss function over weights The gradient of is the error of the jth neuron in the lth layer, is the activation value of the jth neuron in the l-1th layer.

9. A safe operation monitoring and alarm device for a new energy microgrid, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the functions of the safe operation monitoring and alarm system of the new energy microgrid as described in any one of claims 1 to 8 are realized.

10. A readable storage medium, characterized in that: The readable storage medium stores a computer program, which, when executed by a processor, implements the functions of the safe operation monitoring and alarm system of the new energy microgrid as claimed in any one of claims 1 to 8.

Images