Novel intelligent energy storage power station fault detection method and system

Abstract

The invention discloses a novel intelligent energy storage power station fault detection method and system, relates to the technical field of fault detection, and solves the technical problems that diagnosis and analysis are performed depending on a known fault mode and limited information in a database, and the requirements of efficient and reliable operation of a modern energy storage power station cannot be met. When the state abnormal information is analyzed, the historical data is accurately screened with the abnormal parameters as the standard, the to-be-analyzed record highly related to the current fault is rapidly positioned, then the abnormal workpiece is accurately determined, and in the abnormal workpiece information analysis process, the change condition of the abnormal parameters is concerned, and the analysis accuracy of the abnormal workpiece information is improved. Comprising a maximum peak value, a minimum peak value and a numerical value change trend, and multi-dimensional matching with secondary screening records is carried out in combination with abnormal appearance expressions of abnormal workpieces, such as color change, deformation and leakage, so that misdiagnosis caused by single factor analysis is avoided, and the reliability of fault diagnosis is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of fault detection, and in particular to a novel intelligent energy storage power station fault detection method and system. Background Art

[0002] As the demand for energy storage continues to grow, the scale and complexity of energy storage power stations are increasing. During the operation of energy storage power stations, their working status is affected by many factors, such as battery aging, electrical component failure, environmental changes, and unreasonable control strategies, which may cause various failures in energy storage power stations.

[0003] The patent application with publication number CN117330963B discloses a method, system and device for fault detection of an energy storage power station, including: obtaining comprehensive battery information of a battery to be detected in the energy storage power station, and establishing a battery model of the battery to be detected according to the comprehensive battery information; based on the battery model, determining an initial state point matrix and a predicted measurement value corresponding to the battery to be detected, and performing state estimation on the battery to be detected in the energy storage power station according to the initial state point matrix and the predicted measurement value, in combination with process noise parameters of the battery to be detected, and determining a state estimation value; constructing a feature set to be detected by combining the state estimation value through a pre-constructed fault detection model, and performing fault detection on the battery to be detected according to the feature set to be detected and in combination with a preset combined kernel function, wherein the combined kernel function includes a first kernel function and a second kernel function for linear combination, a disturbance term and a polynomial degree are introduced into the first kernel function, and a control weighting parameter is introduced into the second kernel function.

[0004] However, traditional fault detection methods often rely on known fault modes and limited information in the database. It is difficult to quickly and accurately diagnose and analyze some new faults or abnormal data features that are not recorded in the database, and cannot meet the requirements of efficient and reliable operation of modern energy storage power stations. Moreover, when faced with complex and changeable fault conditions, traditional methods lack effective assessment of potential risks of faults, making it difficult to take targeted preventive measures in advance, which can easily lead to the expansion of faults, affect the safety and stability of energy storage power stations, and may even have an adverse impact on the operation of the entire power system. Summary of the invention

[0005] In view of the shortcomings of the prior art, the present invention provides a new intelligent energy storage power station fault detection method and system, which solves the problem that diagnosis and analysis rely on known fault modes and limited information in the database, and cannot meet the requirements of efficient and reliable operation of modern energy storage power stations.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: a new intelligent energy storage power station fault detection method, the method specifically comprises the following steps: Step 1: Collect the energy storage parameters of the energy storage power station, and determine the working status of the energy storage power station according to the energy storage parameters to generate a status result, and the status result includes normal status information and abnormal status information; Step 2: Analyze the obtained status abnormal information, obtain the records to be analyzed by matching the abnormal parameters with the historical data, and determine the abnormal artifacts according to the records to be analyzed to generate abnormal artifact information; Step 3: Analyze the abnormal workpiece information obtained, analyze the changes in abnormal parameters, and match and screen the records to be analyzed to obtain secondary screening records. At the same time, match the secondary screening records with the abnormal characteristics of the abnormal parameters to generate matching results; Step 4: Analyze the successful matching results, calculate the potential risk value corresponding to the fault cause, and judge the dangerous situation of the fault cause according to the potential risk value to generate danger judgment information; Step 5: Analyze the failed matching results, analyze the periodic abnormal features corresponding to the abnormal workpiece information, and determine the cause of the failure by combining the associated parameters of the periodic abnormal features.

[0007] As a further solution of the present invention, the specific method of generating the status result in step 1 is: The energy storage parameters and normal parameters of the energy storage power station are obtained, and the obtained energy storage parameters are compared with the normal parameters. If the energy storage parameters are different from the normal parameters, it means that the state of the energy storage power station is abnormal, and abnormal state information is generated. Conversely, if the energy storage parameters are the same as the normal parameters, it means that the state of the energy storage power station is normal, and normal state information is generated.

[0008] As a further solution of the present invention, the specific method of generating abnormal workpiece information in step 2 is: Obtain the abnormal parameters and historical data corresponding to the abnormal status information, match the values ​​corresponding to the abnormal parameters with the historical data, and filter out the data matching the abnormal data in the historical data to obtain the records to be analyzed; At the same time, the faulty workpiece corresponding to the record to be analyzed is obtained, and the current abnormal parameters are obtained, the fault parameters of the faulty workpiece are matched with the abnormal parameters to determine the abnormal workpiece, and the abnormal workpiece information is generated at the same time.

[0009] As a further solution of the present invention, the specific method of analyzing the abnormal workpiece information in step three is: Acquire the abnormal artifact information and the corresponding abnormal parameters, and obtain the changes in the abnormal parameters. At the same time, use the acquired abnormal parameter changes as the standard to filter the records to be analyzed to obtain secondary screening records. Then obtain the abnormal performance corresponding to the abnormal artifact, and match it with the secondary screening records based on the abnormal performance as the matching standard. If the corresponding abnormal performance exists in the secondary screening record, a successful matching result is generated. Otherwise, if the corresponding abnormal performance does not exist in the secondary screening record, a failed matching result is generated.

[0010] As a further solution of the present invention, the specific method of analyzing the successful matching results in step 4 is: Obtain the secondary screening records corresponding to the successful matching results, and obtain the corresponding fault causes at the same time. Then obtain the number of faults C of the fault cause within the time T, the fault time interval Tp corresponding to the fault cause, and obtain the fault change value Z corresponding to the fault cause. Then substitute the obtained parameters into the formula The potential risk value R is calculated and compared with the preset risk value Ry to generate risk judgment information.

[0011] As a further solution of the present invention, the specific method of comparing the potential risk value with the risk preset value to generate the risk judgment information in step 4 is: If the potential risk value R is greater than the risk preset value Ry, a risk signal is generated. Conversely, if the potential risk value R is less than the risk preset value Ry, a warning signal is generated. The risk signal and the warning signal are further combined to obtain danger judgment information.

[0012] As a further solution of the present invention, the specific method of analyzing the failed matching results in step 5 is: The abnormal workpiece corresponding to the failed matching result is obtained, and the abnormal features corresponding to the abnormal workpiece are obtained at the same time. The periodic changes of the abnormal features with time t1 as the period are obtained and recorded as periodic abnormal features. Then, the associated parameters corresponding to the periodic abnormal features are obtained. By drawing correlation charts of the data, performing principal component analysis and other methods, the potential relationships and new features hidden in the data are discovered, and the cause of the failure is generated.

[0013] A novel intelligent energy storage power station fault detection system includes an energy storage parameter acquisition module, an abnormal state analysis module, a fault analysis and determination module, and an information output module; The energy storage parameter acquisition module is used to collect energy storage parameters, judge the state of the energy storage power station according to the energy storage parameters to generate a state result, and transmit the state abnormality information in the state result to the abnormal state analysis module; Abnormal state analysis module, which analyzes the obtained abnormal state information, obtains records to be analyzed by matching and screening abnormal parameters with historical data, determines abnormal workpieces based on the records to be analyzed, generates abnormal workpiece information, analyzes changes in abnormal parameters, matches and screens with the records to be analyzed, obtains secondary screening records, and matches the secondary screening records with abnormal features of abnormal parameters to generate matching results, and then transmits the generated matching results to the fault analysis determination module; A fault analysis and determination module analyzes the successful matching results obtained, calculates the potential risk value corresponding to the fault cause, and determines the dangerous situation of the fault cause according to the potential risk value, generates dangerous judgment information, and transmits the dangerous judgment information to the information output module, analyzes the failed matching results obtained, analyzes the periodic abnormal characteristics corresponding to the abnormal workpiece information, and determines the fault cause by combining the associated parameters of the periodic abnormal characteristics, and then transmits the generated fault cause to the information output module; The information output module is used to display the acquired danger judgment information and fault causes to the corresponding operators.

[0014] The present invention provides a novel intelligent energy storage power station fault detection method and system. Compared with the prior art, it has the following beneficial effects: The present invention uses abnormal parameters as a standard to accurately screen historical data when analyzing state abnormal information, quickly locates the records to be analyzed that are highly related to the current fault, and then accurately determines the abnormal workpiece. In the process of analyzing the abnormal workpiece information, not only the changes in abnormal parameters, including the maximum peak value, the minimum peak value and the trend of value changes, are paid attention to, but also the abnormal appearance of the abnormal workpiece, such as discoloration, deformation, leakage, etc., is combined with the secondary screening records for multi-dimensional matching, thereby avoiding misdiagnosis caused by single factor analysis and improving the reliability of fault diagnosis. For successful matching results, by introducing parameters such as the number of faults, fault time interval and fault change value, a scientific and reasonable formula is used to calculate the potential risk value, and compared with the preset risk value, so as to generate accurate danger judgment information. When dealing with failed matching results, a method of deep mining of periodic abnormal characteristics and their associated parameters is adopted, combined with data mining algorithms and a variety of data analysis methods, such as association rule mining, cluster analysis, principal component analysis, etc., to discover the potential relationships and new features hidden in the data, so as to determine the cause of the fault. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It is a step method diagram of the present invention; Figure 2 This is a block diagram of the system principle of the present invention. DETAILED DESCRIPTION

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

[0017] See also Figure 1 The present application provides a novel intelligent energy storage power station fault detection method, which specifically includes the following steps: Step 1: Collect the energy storage parameters of the energy storage power station, and determine the working status of the energy storage power station based on the energy storage parameters to generate status results.

[0018] The voltage, current and frequency of the energy storage power station are obtained, and the normal parameters corresponding to the energy storage power station are obtained. The voltage value is stable between 380V and 400V (this range is the normal discharge voltage range obtained based on the normal operation data of the power station in the past), and the current changes steadily according to the rule of decreasing by 0.5A every 5 minutes (which is also the conventional current change trend during normal discharge). The frequency is always stable and maintained within the normal fluctuation range of 50Hz±0.2Hz. The obtained energy storage parameters are compared with the normal parameters. If the energy storage parameters are different from the normal parameters, it means that the state of the energy storage power station is abnormal, and the abnormal state information is generated. On the contrary, if the energy storage parameters are the same as the normal parameters, it means that the state of the energy storage power station is normal, and the normal state information is generated. Specifically, for the normal state of the energy storage power station, it is monitored normally.

[0019] During a certain operation, the voltage collected by the monitoring system suddenly dropped to 300V, which was significantly lower than the lower limit of the normal discharge voltage range (380V). The current also showed irregular and large fluctuations, with fluctuations exceeding 2A every 2 minutes (under normal circumstances, current fluctuations are relatively stable and slow). Although the frequency was still around 50Hz, the fluctuation range expanded to ±0.5Hz (exceeding the normal fluctuation range of ±0.2Hz). In this case, the energy storage parameters are different from the normal parameters, which means that the overall state of the energy storage power station is abnormal.

[0020] Step 2: Analyze the obtained status abnormal information, obtain the records to be analyzed by matching the abnormal parameters with the historical data, and determine the abnormal artifacts according to the records to be analyzed to generate abnormal artifact information.

[0021] Acquire the abnormal parameters corresponding to the abnormal state information, and acquire historical data at the same time, and the historical data is all the fault maintenance data of the energy storage power station within the time T, and then filter the historical data based on the abnormal parameters to obtain the records to be analyzed, and the specific filtering method here is: match the values ​​corresponding to the abnormal parameters with the historical data, filter out the data in the historical data that match the abnormal data, and the matching is indicated by the difference between the abnormal parameters and the historical data being less than the preset value, and the specific value of the preset value is set by the operator; Suppose that a certain energy storage power station detects an abnormal output voltage of the battery pack during operation, and the currently monitored abnormal voltage value is 420V (the normal operating voltage range is 380V-400V). The system then obtains this abnormal parameter and retrieves all the fault maintenance data of the energy storage power station in the past 6 months (i.e. time) from the database. The operator sets the preset difference of the voltage parameter to 5V (i.e. preset value) based on past experience and understanding of the equipment of the power station. When filtering historical data, the system will calculate the difference between the battery pack voltage value in each historical data and the current abnormal voltage value of 420V. For example, the battery pack voltage value of one of the historical data records is 418V, and the difference between it and 420V is 2V, which is less than the preset 5V, then this historical data will be filtered out as a record to be analyzed.

[0022] Then, the filtered records to be analyzed are obtained, and the faulty workpiece corresponding to the records to be analyzed is obtained, and the current abnormal parameters are obtained. The fault parameters of the faulty workpiece are matched with the abnormal parameters to determine the abnormal workpiece, and the fault parameters here are represented as the abnormal parameters corresponding to the faulty workpiece, and the abnormal workpiece information is generated at the same time.

[0023] Step 3: Analyze the abnormal workpiece information obtained, analyze the changes in abnormal parameters, and match and screen the records to be analyzed to obtain secondary screening records. At the same time, match the secondary screening records with the abnormal characteristics of the abnormal parameters to generate matching results.

[0024] Acquire the abnormal workpiece information and the corresponding abnormal parameters, and acquire the changes of the abnormal parameters, and the changes of the abnormal parameters are specifically expressed as the numerical changes within the time t and the maximum peak value and the minimum peak value corresponding to the abnormal parameters. At the same time, the acquired abnormal parameter changes are used as the standard to screen the records to be analyzed to obtain the secondary screening records, and then the abnormal performance corresponding to the abnormal workpiece is acquired, and the abnormal performance here refers to the status performance of the corresponding abnormal components, such as discoloration, deformation, leakage, looseness or bulging on the shell, and the abnormal performance is used as the matching standard to match the secondary screening records. If the corresponding abnormal performance exists in the secondary screening record, a successful matching result is generated. Otherwise, if the corresponding abnormal performance does not exist in the secondary screening record, a failed matching result is generated.

[0025] For example, in the battery management system of a certain energy storage power station, a battery module (abnormal workpiece) is detected to be abnormal. The abnormal parameter obtained by the detection system is the temperature of the battery module. In the past 2 hours (time t), the temperature has gradually increased from the initial 30°C to 60°C (maximum peak) and 28°C (due to a brief abnormality of the cooling fan, the temperature dropped slightly, forming a minimum peak), and the overall trend is continuous increase (value change). This abnormal performance is matched with the secondary screening records. One of the records shows that in the previous fault case, the battery cell shell also bulged, and the temperature rose abnormally due to an internal short circuit in the battery. The problem was finally solved by replacing the faulty battery cell. Therefore, the system generates a successful matching result. Suppose in another detection, it is found that the output current of the inverter (abnormal workpiece) of an energy storage power station is abnormal. The current fluctuates violently within 1 hour, with a maximum value of 150A and a minimum value of 80A (the normal operating range should be 100A-120A), and there is no obvious regular value change. After the same screening process was used to obtain the secondary screening records, the inverter was inspected and it was found that its heat sink had slight discoloration (abnormal performance). However, no similar historical cases of heat sink discoloration and abnormal current fluctuations were found in the secondary screening records. At this time, the system generated a failed match result.

[0026] Step 4: Analyze the successful matching results, calculate the potential risk value corresponding to the fault cause, and judge the dangerous situation of the fault cause according to the potential risk value to generate danger judgment information.

[0027] Obtain the secondary screening records corresponding to the successful matching results, and obtain the corresponding fault causes at the same time. Then obtain the number of faults C of the fault causes within the time T, and the fault time interval Tp corresponding to the fault causes. The fault time interval here is the mean time interval. For example, if the number of faults is three, calculate the time intervals corresponding to two adjacent times respectively, and then sum up the calculated time intervals to calculate the average value, and obtain the fault change value Z corresponding to the fault cause. The fault change value here is expressed as the abnormal parameter change value corresponding to a single fault. Then substitute the obtained parameters into the formula The potential risk value R is calculated, where the exponential term in the formula It is used to further amplify the impact of the number of faults and the time interval between faults on the potential risk value. When the number of faults is large and the time interval between faults is short, the value of this item will increase significantly. e is a natural constant with a value of 2.71. The calculated potential risk value R is compared with the preset risk value Ry. The specific value of the preset risk value is set by the operator based on historical data and experience. If the potential risk value R is greater than the risk preset value Ry, it means that the current cause of the fault is dangerous and a risk signal is generated. Conversely, if the potential risk value R is less than the risk preset value Ry, it means that the current cause of the fault is potentially dangerous and a warning signal is generated. The risk signal and the warning signal are further combined to obtain danger judgment information.

[0028] Step 5: Analyze the failed matching results, analyze the periodic abnormal features corresponding to the abnormal workpiece information, and determine the cause of the failure by combining the associated parameters of the periodic abnormal features.

[0029] The abnormal workpiece corresponding to the failed matching result is obtained, and the abnormal features corresponding to the abnormal workpiece are obtained at the same time. The periodic changes of the abnormal features with time t1 as the period are obtained and recorded as periodic abnormal features. The specific value of t1 is set by the operator. Then the associated parameters corresponding to the periodic abnormal features are obtained. Data mining algorithms, such as association rule mining, cluster analysis, anomaly detection algorithms, etc., are used to deeply mine a large amount of operating data. By drawing correlation charts of the data, performing principal component analysis and other methods, the potential relationships and new features hidden in the data are discovered, and the cause of the fault is generated.

[0030] Taking the battery module of a certain energy storage power station as an example, a failed matching result occurred during a fault diagnosis process. The battery module was confirmed to be an abnormal workpiece. Through detection, its abnormal characteristics included voltage imbalance of battery cells, voltage of some cells was significantly lower than the normal level, and the battery module shell had slight signs of heating.

[0031] The time period was set to 1 hour, and these abnormal characteristics were continuously monitored. The results showed that the voltage imbalance degree would fluctuate significantly every 15 minutes. This periodic voltage abnormal fluctuation pattern is the periodic abnormal characteristic.

[0032] Further analysis was conducted on parameters associated with the cycle abnormality, such as the charge and discharge current of the battery module, battery temperature distribution, ambient temperature, etc. Using the association rule mining algorithm, it was found that when the charge and discharge current changes in a specific range (such as 50A-60A), the cycle abnormality of voltage imbalance is more significant, and the battery temperature distribution also shows an uneven increase trend, especially in the center of the battery module, where the temperature rises faster.

[0033] By drawing a correlation chart, we can clearly see that there is a strong positive correlation between the charge and discharge current and the voltage imbalance, and there is also a certain correlation between the ambient temperature and the temperature increase in the center of the battery module. Then, using principal component analysis, we reduced the dimension of these related parameters and extracted the key principal components. We found that one of the principal components mainly reflects the comprehensive influencing factors of the electrochemical reaction rate and heat conduction efficiency inside the battery.

[0034] Based on the above in-depth research results, it is speculated that the cause of the failure may be that some of the battery connectors inside the battery module are loose, resulting in increased contact resistance. During the charging and discharging process, especially when the current is large, the heat generated by the contact resistance causes the battery temperature to rise unevenly, which in turn affects the electrochemical reaction of the battery, causing voltage imbalance, and this effect presents a periodic fluctuation feature, because the change in current also has a certain periodic law.

[0035] Embodiment 2: This embodiment is implemented on the basis of Embodiment 1, and the difference from Embodiment 1 is as follows: The determination of the cause of the fault in step five can also be determined by comparing similar systems and cases, collecting operating data and fault cases of other energy storage power stations of the same type, and looking for situations with similar abnormal data characteristics. Although different energy storage power stations may have certain differences, similar system structures and operating principles may cause them to face some common problems. Through comparative analysis, we can learn from the causes and solutions of faults in other power stations to provide ideas for analyzing the abnormal data characteristics of the current power station. For example, if it is found that the abnormal temperature rise of the battery pack of this power station is similar to that of other power stations, you can refer to their processing experience to check whether there are problems with the heat dissipation system, the temperature control strategy of the battery management system, etc.; Find inspiration from similar systems in other related fields, such as electric vehicle battery management systems, uninterruptible power supplies (UPS), etc. These systems are similar to energy storage power stations in some aspects, such as battery charge and discharge management and energy conversion. Drawing on their fault analysis methods and experience will help discover the causes of abnormal data features not covered in the database.

[0036] Embodiment 3, as the embodiment 3 of the present invention, focuses on combining the implementation processes of embodiment 1 and embodiment 2 for implementation.

[0037] Example 4, please refer to Figure 2 The present application provides a novel intelligent energy storage power station fault detection system, including: energy storage parameter acquisition module, abnormal state analysis module, fault analysis determination module and information output module, and combined with Figure 2 It can be known that the above functional modules are electrically connected in a unidirectional manner.

[0038] An energy storage parameter acquisition module, which is used to collect energy storage parameters, and at the same time, judge the state of the energy storage power station according to the energy storage parameters to generate a state result, and transmit the state abnormality information in the state result to the abnormal state analysis module, and the processing method here is the same as the processing process of step 1 in embodiment 1; An abnormal state analysis module, which analyzes the obtained state abnormal information, obtains records to be analyzed by matching and screening abnormal parameters with historical data, and generates abnormal workpiece information by determining abnormal workpieces according to the records to be analyzed. The processing method here is the same as the processing process of step 2 in embodiment 1. At the same time, the obtained abnormal workpiece information is analyzed, and secondary screening records are obtained by analyzing the changes in abnormal parameters and matching and screening with the records to be analyzed. At the same time, the secondary screening records are matched in combination with the abnormal characteristics of the abnormal parameters to generate matching results, and then the generated matching results are transmitted to the fault analysis and determination module. The processing method here is the same as the processing process of step 3 in embodiment 1. A fault analysis and determination module, which analyzes the obtained successful matching results, calculates the potential risk value corresponding to the fault cause, and determines the dangerous situation of the fault cause according to the potential risk value, generates danger judgment information, and transmits the danger judgment information to the information output module, and the specific processing method is the same as the processing process of step 4 in embodiment 1, analyzes the obtained failed matching results, analyzes the periodic abnormal characteristics corresponding to the abnormal workpiece information, and determines the fault cause by combining the associated parameters of the periodic abnormal characteristics, and then transmits the generated fault cause to the information output module, and the processing method here is the same as the processing process of step 5 in embodiment 1; The information output module is used to display the acquired danger judgment information and fault causes to the corresponding operators.

[0039] Some of the data in the above formulas are dimensionless and numerically calculated. Meanwhile, the contents not described in detail in this specification belong to the prior art known to those skilled in the art.

[0040] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A novel intelligent energy storage power station fault detection method, characterized in that: The method specifically comprises the following steps: Step 1: Collect the energy storage parameters of the energy storage power station, and determine the working status of the energy storage power station according to the energy storage parameters to generate a status result, and the status result includes normal status information and abnormal status information; Step 2: Analyze the obtained status abnormal information, obtain the records to be analyzed by matching the abnormal parameters with the historical data, and determine the abnormal artifacts according to the records to be analyzed to generate abnormal artifact information; Step 3: Analyze the abnormal workpiece information obtained, analyze the changes in abnormal parameters, and match and screen the records to be analyzed to obtain secondary screening records. At the same time, match the secondary screening records with the abnormal characteristics of the abnormal parameters to generate matching results; Step 4: Analyze the successful matching results, calculate the potential risk value corresponding to the fault cause, and judge the dangerous situation of the fault cause according to the potential risk value to generate danger judgment information; Step 5: Analyze the failed matching results, analyze the periodic abnormal features corresponding to the abnormal workpiece information, and determine the cause of the failure by combining the associated parameters of the periodic abnormal features.

2. A novel intelligent energy storage power station fault detection method according to claim 1, characterized in that: The specific method of generating the status result in step 1 is: The energy storage parameters and normal parameters of the energy storage power station are obtained, and the obtained energy storage parameters are compared with the normal parameters. If the energy storage parameters are different from the normal parameters, it means that the state of the energy storage power station is abnormal, and abnormal state information is generated. Conversely, if the energy storage parameters are the same as the normal parameters, it means that the state of the energy storage power station is normal, and normal state information is generated.

3. A novel intelligent energy storage power station fault detection method according to claim 1, characterized in that: The specific method of generating abnormal workpiece information in step 2 is: Obtain the abnormal parameters and historical data corresponding to the abnormal status information, match the values ​​corresponding to the abnormal parameters with the historical data, and filter out the data matching the abnormal data in the historical data to obtain the records to be analyzed; At the same time, the faulty workpiece corresponding to the record to be analyzed is obtained, and the current abnormal parameters are obtained, the fault parameters of the faulty workpiece are matched with the abnormal parameters to determine the abnormal workpiece, and the abnormal workpiece information is generated at the same time.

4. A novel intelligent energy storage power station fault detection method according to claim 1, characterized in that: The specific method of analyzing abnormal workpiece information in step 3 is: Acquire the abnormal artifact information and the corresponding abnormal parameters, and obtain the changes in the abnormal parameters. At the same time, use the acquired abnormal parameter changes as the standard to filter the records to be analyzed to obtain secondary screening records. Then obtain the abnormal performance corresponding to the abnormal artifact, and match it with the secondary screening records based on the abnormal performance as the matching standard. If the corresponding abnormal performance exists in the secondary screening record, a successful matching result is generated. Otherwise, if the corresponding abnormal performance does not exist in the secondary screening record, a failed matching result is generated.

5. A novel intelligent energy storage power station fault detection method according to claim 1, characterized in that: The specific method of analyzing the successful matching results in step 4 is as follows: Obtain the secondary screening records corresponding to the successful matching results, and obtain the corresponding fault causes at the same time. Then obtain the number of faults C of the fault causes within the time T, the fault time interval Tp corresponding to the fault causes, and obtain the fault change value Z corresponding to the fault causes. Then substitute the obtained parameters into the formula The potential risk value R is calculated and compared with the preset risk value Ry to generate risk judgment information.

6. A novel intelligent energy storage power station fault detection method according to claim 5, characterized in that: The specific method of comparing the potential risk value with the risk preset value to generate the risk judgment information in step 4 is: If the potential risk value R is greater than the risk preset value Ry, a risk signal is generated. Conversely, if the potential risk value R is less than the risk preset value Ry, a warning signal is generated. The risk signal and the warning signal are further combined to obtain danger judgment information.

7. A novel intelligent energy storage power station fault detection method according to claim 1, characterized in that: The specific method of analyzing the failed matching results in step 5 is: The abnormal workpiece corresponding to the failed matching result is obtained, and the abnormal features corresponding to the abnormal workpiece are obtained at the same time. The periodic changes of the abnormal features with time t1 as the period are obtained and recorded as periodic abnormal features. Then, the associated parameters corresponding to the periodic abnormal features are obtained. By drawing correlation charts of the data, performing principal component analysis and other methods, the potential relationships and new features hidden in the data are discovered, and the cause of the failure is generated.

8. A novel intelligent energy storage power station fault detection system, used to execute a novel intelligent energy storage power station fault detection method according to any one of claims 1 to 7, characterized in that: It includes an energy storage parameter acquisition module, an abnormal state analysis module, a fault analysis and determination module, and an information output module.

9. A novel intelligent energy storage power station fault detection system according to claim 8, characterized in that: The energy storage parameter acquisition module is used to collect energy storage parameters, and at the same time judge the state of the energy storage power station according to the energy storage parameters to generate a state result, and transmit the state abnormality information in the state result to the abnormal state analysis module; Abnormal state analysis module, which analyzes the obtained abnormal state information, obtains records to be analyzed by matching and screening abnormal parameters with historical data, determines abnormal workpieces based on the records to be analyzed, generates abnormal workpiece information, analyzes changes in abnormal parameters, matches and screens with the records to be analyzed, obtains secondary screening records, and matches the secondary screening records with abnormal features of abnormal parameters to generate matching results, and then transmits the generated matching results to the fault analysis determination module; A fault analysis and determination module analyzes the successful matching results obtained, calculates the potential risk value corresponding to the fault cause, and determines the dangerous situation of the fault cause according to the potential risk value, generates dangerous judgment information, and transmits the dangerous judgment information to the information output module, analyzes the failed matching results obtained, analyzes the periodic abnormal characteristics corresponding to the abnormal workpiece information, and determines the fault cause by combining the associated parameters of the periodic abnormal characteristics, and then transmits the generated fault cause to the information output module; The information output module is used to display the acquired danger judgment information and fault causes to the corresponding operators.

Images