Power management system for storage battery of direct-current system of transformer substation

Abstract

The invention discloses a power management system for a transformer substation direct current system storage battery, which comprises a storage battery pack monitoring unit and a single battery monitoring unit, wherein the storage battery pack monitoring unit and the single battery monitoring unit are used for acquiring data of a storage battery pack and a single battery in charging, discharging and running processes; the battery pack monitoring unit and the single battery monitoring unit are respectively connected with the data processing unit through the communication transceiving unit, and the data processing unit is connected with the performance evaluation unit, the state prediction unit and the data display unit. The performance evaluation unit and the state prediction unit are used for evaluating the performance condition of the storage battery pack and predicting the charging and discharging state based on the acquired storage battery pack data and the single battery data; the data display unit is used for displaying various monitoring data of the storage battery pack and the single battery, a performance evaluation result and a state prediction result; the operation state of the transformer substation direct current system storage battery pack can be monitored, performance and state evaluation is carried out on the storage battery pack, and the overall operation state of the storage battery pack can be mastered in real time.

Description

Technical Field

[0001] This invention belongs to the field of battery management technology for substation DC systems, and specifically relates to a power management system for substation DC system batteries. Background Technology

[0002] The DC power supply system of a substation is a backup power source for the substation. The battery bank, as an independent power source unaffected by the AC power supply, can continue to provide power to the substation's protection automation devices, emergency lighting, emergency power supply, signaling equipment, and circuit breaker opening and closing operations when the AC power supply of the rectifier system fails or malfunctions. Its stable voltage and large capacity make it suitable for complex protection devices and is the core of the substation DC power supply system.

[0003] With the continuous increase in electricity demand and the development of new energy technologies, the construction of smart substations has accelerated. A large number of smart secondary devices have been put into use, requiring reliable power supply from DC systems. This has led to the increasingly widespread application of battery banks in power systems. However, due to the complexity of the operating environment and the frequent changes in parameters during charging and discharging, real-time monitoring and management of battery banks have become crucial.

[0004] Therefore, in order to solve the above problems, it is necessary to develop a power management system for substation DC system batteries. Summary of the Invention

[0005] The purpose of this invention is to overcome the shortcomings of the prior art and provide a power management system for substation DC system batteries, which monitors the operation of substation DC system battery banks and evaluates their performance and status, so as to facilitate real-time monitoring of the overall operation of the battery banks.

[0006] The objective of this invention is achieved as follows: a power management system for batteries in a substation DC system, comprising a battery pack monitoring unit, a single cell monitoring unit, a communication transceiver unit, a data processing unit, a performance evaluation unit, a status prediction unit, and a data display unit;

[0007] The battery pack monitoring unit collects battery pack data during charging, discharging, and operation. The individual battery monitoring unit collects individual battery data during charging, discharging, and operation. The battery pack monitoring unit and the individual battery monitoring unit are connected to the data processing unit via a communication transceiver unit. The data processing unit is connected to a performance evaluation unit, a state prediction unit, and a data display unit. The performance evaluation unit evaluates the overall performance of the battery pack based on the collected battery pack data and individual battery data. The state prediction unit predicts the charging and discharging state of the battery pack based on the collected battery pack data and individual battery data. The data display unit displays various monitoring data of the battery pack and individual batteries, as well as the performance evaluation results and state prediction results.

[0008] Furthermore, it also includes a power supply unit, which is used to provide the power required for operation to the battery pack monitoring unit, the individual battery monitoring unit, the communication transceiver unit, the data processing unit, the performance evaluation unit, the status prediction unit, and the data display unit, respectively.

[0009] Furthermore, the battery pack monitoring unit includes a battery pack voltage monitoring module, a battery pack current monitoring module, and a temperature and humidity monitoring module, which are used to collect data on the voltage, current, and ambient temperature and humidity of the battery pack during charging, discharging, and operation, respectively. Specifically, the battery pack current monitoring module is implemented using an on / off Hall current sensor, the battery pack voltage monitoring module converts the current signal into a voltage signal through a sampling resistor and amplifies it to obtain voltage data for analog-to-digital conversion, and the temperature and humidity monitoring module is implemented using an SHTC3 temperature and humidity sensor.

[0010] Furthermore, the single-cell battery monitoring unit includes a single-cell voltage monitoring module, an internal resistance monitoring module, and a terminal temperature monitoring module, which respectively collect data on the voltage, internal resistance, and negative terminal temperature of the single-cell battery during charging, discharging, and operation. Specifically, the voltage monitoring module uses a linear sampling circuit composed of operational amplifiers to collect the terminal voltage of the single-cell battery; the internal resistance monitoring module uses instantaneous pulse discharge to test the internal resistance of the single-cell battery; and the temperature monitoring module uses a high-precision NTC thermistor to monitor the negative terminal temperature.

[0011] Furthermore, the performance evaluation unit specifically employs an improved K-means clustering algorithm to evaluate the performance of the battery pack; specifically, it includes the following steps: assuming a battery pack contains n individual batteries, the battery pack is denoted as a set. The historical voltage data corresponding to each sample is denoted as ; ① Initialize parameters; ② Set the battery pack sample set Each sample is assigned to a specific category. This indicates that a battery pack contains Individual battery cells; ③ Based on the minimum number of samples allowed in each category. Determine whether the category is true; if the category is true... Number of samples Then cancel the center of that class. Let the initial number of cluster centers be... And return to step ②; ④ Calculate the center and average intra-class distance of each category after classification. and overall average distance Perform calculations; ⑤ Calculate the distance between the centers of each category. and the lower bound of the minimum distance between it and the two types of centers. Compare and select those less than the minimum distance lower limit. The categories are arranged according to distance Sort by size in ascending order, take the first... One, starting from the smallest This involves merging two clusters belonging to the same class and calculating the cluster centers of the merged clusters. In one iteration, a class can be merged at most once, and let... ⑥ Determine if the number of iterations has reached the maximum or the process has converged. If so, the iteration ends; otherwise, increment the number of iterations by 1 and return to step ②.

[0012] Furthermore, in step ④, the intra-class distance is represented by the Euclidean distance from each data group to the cluster center: , Represents sample data, Indicates the cluster center. This indicates the number of samples in the battery pack. Represents the number of cluster centers; average intra-cluster distance. and overall average distance Based on respectively The average is obtained by calculating the within-class average and the overall average.

[0013] Furthermore, the distance between the centers of each category in step ⑤ , .

[0014] Furthermore, the state prediction unit specifically employs an LSTM model to predict the charge and discharge states of the battery pack, wherein the LSTM model includes a forget gate. Input gate Output gate Specifically, it is expressed as: , , , , , In the formula: , , , , , , , These are the corresponding weight coefficient matrix and bias term, respectively. , These are the sigmoid function and the hyperbolic tangent activation function, respectively. For the unit state, This is for backup update content. , This is the output value of the LSTM at the current time step and the previous time step.

[0015] The beneficial effects of this invention, achieved by adopting the above technical solution, are as follows: By setting up a battery pack monitoring unit and a single-cell monitoring unit to collect operating data of the battery pack and individual cells respectively, the data is transmitted to a data processing unit for processing and then displayed intuitively through a data display unit. Furthermore, the performance status of the battery pack and the charge / discharge status are evaluated and predicted through a performance evaluation unit and a status prediction unit. This facilitates maintenance personnel in understanding the battery's operating status, saves manpower and resources for substation maintenance, improves maintenance efficiency, reduces the probability of accidents, and ensures the stable and reliable operation of the substation's DC system. Attached Figure Description

[0016] Figure 1 This is a schematic diagram of the principle of the present invention. Detailed Implementation

[0017] The technical solution of the present invention will be further described in detail below through embodiments and in conjunction with the accompanying drawings.

[0018] like Figure 1 As shown, a power management system for a substation DC system battery includes a battery pack monitoring unit, a single cell monitoring unit, a communication transceiver unit, a data processing unit, a performance evaluation unit, a status prediction unit, and a data display unit.

[0019] The battery pack monitoring unit is used to collect data during charging, discharging, and operation. Preferably, the battery pack monitoring unit includes a battery pack voltage monitoring module, a battery pack current monitoring module, and a temperature and humidity monitoring module, which are used to collect data on the voltage, current, and ambient temperature and humidity of the battery pack during charging, discharging, and operation, respectively. Specifically, the battery pack current monitoring module is implemented using an open-close Hall current sensor, the battery pack voltage monitoring module converts the current signal into a voltage signal through a sampling resistor and amplifies it to obtain voltage data for analog-to-digital conversion, and the temperature and humidity monitoring module is implemented using an SHTC3 temperature and humidity sensor.

[0020] The single-cell battery monitoring unit is used to collect data from the single-cell batteries during charging, discharging, and operation. The single-cell battery monitoring unit includes a single-cell voltage monitoring module, an internal resistance monitoring module, and a terminal temperature monitoring module, which respectively collect data on the voltage, internal resistance, and negative terminal temperature of the single-cell batteries during charging, discharging, and operation. Specifically, the voltage monitoring module uses a linear sampling circuit composed of operational amplifiers to collect the terminal voltage of the single-cell battery. Specifically, the potentials at both ends of the single-cell battery are connected to the positive and negative terminals of a differential amplifier, respectively. After amplification by the differential amplifier, the data is sent to an analog-to-digital converter for analog-to-digital conversion. The internal resistance monitoring module uses instantaneous pulse discharge to test the internal resistance of the single-cell battery. The temperature monitoring module uses a high-precision NTC thermistor to monitor the negative terminal temperature.

[0021] The battery pack monitoring unit and the individual battery monitoring unit are respectively connected to the data processing unit through a communication transceiver unit. The data processing unit is connected to a performance evaluation unit, a status prediction unit, and a data display unit.

[0022] The performance evaluation unit evaluates the overall performance of the battery pack based on the collected battery pack data and individual cell data.

[0023] Preferably, the performance evaluation unit specifically uses an improved K-means clustering algorithm to evaluate the performance of the battery pack; specifically, it includes the following steps: assuming a battery pack contains n individual batteries, the battery pack is denoted as a set. The historical voltage data corresponding to each sample is denoted as ; ① Initialize parameters; ② Set the battery pack sample set Each sample is assigned to a specific category. This indicates that a battery pack contains Individual battery cells; ③ Based on the minimum number of samples allowed in each category. Determine whether the category is true; if the category is true... Number of samples Then cancel the center of that class. Let the initial number of cluster centers be... And return to step ②; ④ Calculate the center and average intra-class distance of each category after classification. and overall average distance Perform calculations; ⑤ Calculate the distance between the centers of each category. and the lower bound of the minimum distance between it and the two types of centers. Compare and select those less than the minimum distance lower limit. The categories are arranged according to distance Sort by size in ascending order, take the first... One, starting from the smallest This involves merging two clusters belonging to the same class and calculating the cluster centers of the merged clusters. In one iteration, a class can be merged at most once, and let... ⑥ Determine if the number of iterations has reached the maximum or the process has converged. If so, the iteration ends; otherwise, increment the number of iterations by 1 and return to step ②.

[0024] Preferably, in step ④, the intra-class distance is represented by the Euclidean distance from each data group to the cluster center: , Represents sample data, Indicates the cluster center. This indicates the number of samples in the battery pack. Represents the number of cluster centers; average intra-cluster distance. and overall average distance Based on respectively The distance between the center of each category in step ⑤ is obtained by calculating the within-class average and the overall average. , .

[0025] The state prediction unit predicts the charge and discharge state of the battery pack based on the collected battery pack data and individual cell data.

[0026] Preferably, the state prediction unit specifically uses an LSTM model to predict the charge and discharge states of the battery pack, wherein the LSTM model includes a forget gate. Input gate Output gate Specifically, it is expressed as: , , , , , In the formula: , , , , , , , These are the corresponding weight coefficient matrix and bias term, respectively. , These are the sigmoid function and the hyperbolic tangent activation function, respectively. For the unit state, This is for backup update content. , This is the output value of the LSTM at the current time step and the previous time step.

[0027] The data display unit is used to display various monitoring data, performance evaluation results, and status prediction results of the battery pack and individual cells.

[0028] It also includes a power supply unit, which provides the power required for operation to the battery pack monitoring unit, the individual battery monitoring unit, the communication transceiver unit, the data processing unit, the performance evaluation unit, the status prediction unit, and the data display unit.

[0029] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention should be covered within the scope of the claims of the present invention.

Claims

1. A power management system for batteries in a substation DC system, characterized in that: It includes a battery pack monitoring unit, a single cell monitoring unit, a communication transceiver unit, a data processing unit, a performance evaluation unit, a status prediction unit, and a data display unit; The battery pack monitoring unit collects battery pack data during charging, discharging, and operation. The individual battery monitoring unit collects individual battery data during charging, discharging, and operation. The battery pack monitoring unit and the individual battery monitoring unit are connected to the data processing unit via a communication transceiver unit. The data processing unit is connected to a performance evaluation unit, a state prediction unit, and a data display unit. The performance evaluation unit evaluates the overall performance of the battery pack based on the collected battery pack data and individual battery data. The state prediction unit predicts the charging and discharging state of the battery pack based on the collected battery pack data and individual battery data. The data display unit displays various monitoring data of the battery pack and individual batteries, as well as the performance evaluation results and state prediction results.

2. The power management system for a substation DC system battery according to claim 1, characterized in that: It also includes a power supply unit, which provides the power required for operation to the battery pack monitoring unit, the individual battery monitoring unit, the communication transceiver unit, the data processing unit, the performance evaluation unit, the status prediction unit, and the data display unit, respectively.

3. The power management system for a substation DC system battery according to claim 1, characterized in that: The battery pack monitoring unit includes a battery pack voltage monitoring module, a battery pack current monitoring module, and a temperature and humidity monitoring module, which are used to collect data on the battery pack voltage, current, and ambient temperature and humidity during charging, discharging, and operation. Specifically, the battery pack current monitoring module uses an on / off Hall current sensor, the battery pack voltage monitoring module converts the current signal into a voltage signal through a sampling resistor, amplifies it, and obtains the voltage data for analog-to-digital conversion, and the temperature and humidity monitoring module uses an SHTC3 temperature and humidity sensor.

4. A power management system for a substation DC system battery according to claim 1, characterized in that: The single-cell battery monitoring unit includes a single-cell voltage monitoring module, an internal resistance monitoring module, and a terminal temperature monitoring module, which respectively collect data on the voltage, internal resistance, and negative terminal temperature of the single-cell battery during charging, discharging, and operation. Specifically, the voltage monitoring module uses a linear sampling circuit composed of operational amplifiers to collect the terminal voltage of the single-cell battery; the internal resistance monitoring module uses instantaneous pulse discharge to test the internal resistance of the single-cell battery; and the temperature monitoring module uses a high-precision NTC thermistor to monitor the negative terminal temperature.

5. A power management system for a substation DC system battery according to claim 1, characterized in that: The performance evaluation unit specifically uses an improved K-means clustering algorithm to evaluate the performance of the battery pack; specifically, it includes the following steps: Assume a battery pack contains n individual batteries, and denote the battery pack as a set. The historical voltage data corresponding to each sample is denoted as ; ① Initialize parameters; ② Set the battery pack sample set Each sample is assigned to a specific category. This indicates that a battery pack contains Individual battery cells; ③ Based on the minimum number of samples allowed in each category. Determine whether the category is true; if the category is true... Number of samples Then cancel the center of that class. Let the initial number of cluster centers be... And return to step ②; ④ Calculate the center and average intra-class distance of each category after classification. and overall average distance Perform calculations; ⑤ Calculate the distance between the centers of each category. and the lower bound of the minimum distance between it and the two types of centers. Compare and select those less than the minimum distance lower limit. The categories are arranged according to distance Sort by size in ascending order, take the first... One, starting from the smallest This involves merging two clusters belonging to the same class and calculating the cluster centers of the merged clusters. In one iteration, a class can be merged at most once, and let... ⑥ Determine if the number of iterations has reached the maximum or the process has converged. If so, the iteration ends; otherwise, increment the number of iterations by 1 and return to step ②.

6. A power management system for a substation DC system battery according to claim 5, characterized in that: In step ④, the intra-class distance is represented by the Euclidean distance from each data group to the cluster center: , Represents sample data, Indicates the cluster center. This indicates the number of samples in the battery pack. Represents the number of cluster centers; average intra-cluster distance. and overall average distance Based on respectively The average is obtained by calculating the within-class average and the overall average.

7. A power management system for a substation DC system battery according to claim 5, characterized in that: The distance between the centers of each category in step ⑤ , .

8. A power management system for a substation DC system battery according to claim 1, characterized in that: The state prediction unit specifically uses an LSTM model to predict the charge and discharge states of the battery pack. The LSTM model includes a forget gate. Input gate Output gate Specifically, it is expressed as: , , , , , In the formula: , , , , , , , These are the corresponding weight coefficient matrix and bias term, respectively. , These are the sigmoid function and the hyperbolic tangent activation function, respectively. For the unit state, This is for backup update content. , This is the output value of the LSTM at the current time step and the previous time step.

Images