A quality management method and system for a new energy power station

Abstract

This application proposes a quality management method and system for new energy power plants, relating to the field of power plant management. The method includes: receiving a list of component models and quantities for target energy storage units in a target new energy power plant; statistically analyzing the time-series matrix of energy storage impact attributes, energy storage unit samples, and workload time-series information; performing a redundancy lifetime assessment on the target energy storage units based on the workload time-series information to obtain a predicted redundancy lifetime value; and assigning temporary or default periodic quality inspection labels to the target energy storage units. This application solves the technical problem in existing technologies where quality inspection of new energy power plant construction relies solely on periodic monitoring, potentially leading to the omission of critical risk moments and the existence of operational hazards. It achieves the technical effect of conducting redundancy lifetime assessments based on the service data and workload time-series information of energy storage units, enabling targeted quality inspection labels, and effectively preventing operational risks.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of power plant management, and in particular to a quality management method and system for a new energy power plant. BACKGROUND

[0002] With the rapid development of the new energy industry, the construction quality of new energy power plants, as an important carrier of clean energy, is particularly important. Currently, the management of new energy power plants at home and abroad mainly adopts a regular monitoring method, that is, each component of the power plant is detected and evaluated according to a fixed time period, so as to realize the quality management of the new energy power plant. Although this regular monitoring method can find problems in the operation of the power plant to a certain extent, it has great limitations because the detection period is fixed and cannot be flexibly adjusted according to the actual operating state of the power plant. In particular, for key equipment such as storage units, their operating state is affected by various factors such as work load, environmental conditions, etc. These factors may change dramatically in a short period of time, and the regular monitoring method is difficult to capture the potential risks brought by these changes in time. This results in the possibility of missing critical risk moments between two regular detections, thereby laying hidden dangers for the safe operation of the power plant. SUMMARY

[0003] The present application provides a quality management method and system for a new energy power plant to solve the technical problem that the construction quality detection of new energy power plants in the prior art only relies on a regular monitoring method, which may miss critical risk moments and exist operational risks.

[0004] The technical solution of the present application to solve the above technical problem is as follows:

[0005] In a first aspect, the present application provides a quality management method for a new energy power plant, comprising: receiving a list of element types and a list of element quantities of a target storage unit of a target new energy power plant; retrieving service data of the target storage unit of the target new energy power plant, and counting a storage influence attribute time sequence matrix; counting storage unit samples that meet the list of element types and the list of element quantities, and work load time sequence information of the storage influence attribute time sequence matrix; according to the work load time sequence information, performing redundancy life assessment on the target storage unit to obtain a redundancy life prediction value; when the redundancy life prediction value is less than or equal to a redundancy life threshold, temporarily marking the target storage unit for quality detection; and when the redundancy life prediction value is greater than the redundancy life threshold, marking the target storage unit for default period quality detection.

[0006] In a second aspect, the present application provides a quality management system for a new energy power station, comprising: a data receiving module configured to receive a component model list and a component quantity list of a target energy storage unit of a target new energy power station; a service analysis module configured to retrieve service data of the target energy storage unit of the target new energy power station, and to count an energy storage influence attribute time sequence matrix; a load counting module configured to count energy storage unit samples satisfying the component model list and the component quantity list, and working load time sequence information of the energy storage influence attribute time sequence matrix; a life assessment module configured to perform redundancy life assessment on the target energy storage unit according to the working load time sequence information, and to obtain a redundancy life prediction value; a temporary inspection identification module configured to identify temporary quality inspection of the target energy storage unit when the redundancy life prediction value is less than or equal to a redundancy life threshold value; and a default identification module configured to identify default periodic quality inspection of the target energy storage unit when the redundancy life prediction value is greater than the redundancy life threshold value.

[0007] The present application has the following advantages:

[0008] The component model list and the component quantity list of the target energy storage unit of the target new energy power station are received to provide a basis for subsequent analysis of component configuration; the service data of the target energy storage unit of the target new energy power station are retrieved to count the energy storage influence attribute time sequence matrix, thereby providing data support for assessing changes in energy storage system performance; the energy storage unit samples satisfying the component model list and the component quantity list are counted, and the working load time sequence information of the energy storage influence attribute time sequence matrix is obtained to screen out energy storage unit samples with the same configuration, analyze the time sequence characteristics of the working load, and establish a comparable reference benchmark; the redundancy life assessment is performed on the target energy storage unit according to the working load time sequence information to obtain the redundancy life prediction value, thereby predicting the remaining service life of the energy storage unit through working load data analysis and realizing predictive assessment; when the redundancy life prediction value is less than or equal to the redundancy life threshold value, temporary quality inspection of the target energy storage unit is identified to prompt the need for temporary quality inspection and prevent potential failures; and when the redundancy life prediction value is greater than the redundancy life threshold value, default periodic quality inspection of the target energy storage unit is identified to ensure the performance of regular maintenance.

[0009] The above technical solution realizes intelligent quality inspection planning for energy storage units of a new energy power station, adopts different inspection strategies according to different predicted service lives, realizes targeted quality inspection identification, improves the inspection efficiency and resource utilization rate, and effectively prevents operation risks of the energy storage units. BRIEF DESCRIPTION OF DRAWINGS

[0010] Figure 1 A flowchart of a quality management method for a new energy power station provided by the present application is shown in the figure.

[0011] Figure 2A structural schematic diagram of a quality management system of a new energy power station provided by the application.

[0012] In the drawings, the components represented by the respective reference numerals are as follows:

[0013] The data receiving module 11, the service analysis module 12, the load statistics module 13, the life evaluation module 14, the inspection identification module 15, and the default identification module 16. DETAILED DESCRIPTION

[0014] The technical solutions in the embodiments of the application will be apparently and completely described below with reference to the drawings in the embodiments of the application. Obviously, the described embodiments are only part of the embodiments of the application, rather than all the embodiments of the application. Based on the embodiments in the application, all other embodiments obtained by a person skilled in the art without creative work fall within the protection scope of the application.

[0015] In the description of the application, the terms "first", "second", "third", "fourth", "fifth", "sixth" and the like are used only to describe purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the technical features indicated. Therefore, the features defined with "first", "second", "third", "fourth", "fifth", "sixth" and the like can explicitly or implicitly include one or more of the features. In the description of the application, the meaning of "multiple" is two or more, unless otherwise explicitly and specifically limited.

[0016] In the description of the application, the term "for example" is used to indicate "as an example, illustration or explanation". Any embodiment described as "for example" in the application is not necessarily interpreted as more preferred or more advantageous than other embodiments. The following description is given in order to enable any person skilled in the art to implement and use the application. In the following description, details are listed for the purpose of explanation. It should be understood that a person skilled in the art can realize the application without using these specific details. In other examples, well-known structures and processes will not be described in detail in order to avoid unnecessary details making the description of the application obscure. Therefore, the application is not intended to be limited to the shown embodiments, but is consistent with the broadest scope of principles and features disclosed.

[0017] In one embodiment, as shown in the accompanying drawings, the application provides a quality management method of a new energy power station, comprising: Figure 1

[0018] S100: receiving an element model list and an element quantity list of a target energy storage unit of a target new energy power station.

[0019] ​Specifically, the target new energy power station refers to a power station that uses renewable energy such as wind, solar, and tidal energy as its energy source and is equipped with energy storage facilities. Unlike traditional thermal power stations, new energy power stations have the characteristics of environmental protection and sustainability, but they also face technical challenges such as unstable energy input and grid peak shaving demand, so the energy storage system plays a crucial role. The target energy storage unit refers to the functional unit responsible for storing and releasing electrical energy in a new energy power station, which can be composed of various energy storage elements such as lithium-ion battery packs, sodium-sulfur battery packs, flow battery packs, and supercapacitors. The quality and performance of the energy storage unit directly affect the operational stability and electrical energy deployment capability of the entire new energy power station, making it an important object of power station construction quality testing.

[0020] In the quality testing of the energy storage unit, the element model list and the element quantity list of the target energy storage unit of the target new energy power station are first received. The element model list records all the element model information used in the target energy storage unit, including but not limited to battery model, capacitor model, converter model, cooling device model, control module model, etc.; the element quantity list corresponds to the quantity information of each type of element, reflecting the scale and configuration structure of the energy storage unit. In actual application, the above information can be received in various ways, such as: directly obtained from the construction or operation party of the new energy power station through a special data interface; extracted from the database of the power station management system; obtained by scanning and identifying the equipment label of the energy storage unit; or through manual input, etc.

[0021] Different combinations of element models and quantities will form energy storage units of different scales and performance characteristics, which will directly affect the working load capacity, operational stability, and service life of the energy storage unit. Therefore, the element model list and the element quantity list are the key reference for subsequent redundancy life assessment, laying the foundation for accurate quality testing.

[0022] S200: Retrieve the service data of the target energy storage unit of the target new energy power station, and count the energy storage influence attribute time sequence matrix.

[0023] Specifically, while receiving the element model list and the element quantity list, the service data of the target energy storage unit of the target new energy power station is retrieved, and the energy storage influence attribute time sequence matrix is counted. Service data refers to various operating parameter records generated by the energy storage unit during actual operation, including but not limited to charge-discharge times, charge-discharge depth, operating temperature, voltage and current changes, environmental humidity, power output, and other real-time monitoring data. These data comprehensively reflect the performance of the energy storage unit under different working conditions and environmental conditions, and are the basic materials for quality assessment.

[0024] The storage electricity influence attribute time sequence matrix is a multi-dimensional data structure formed after systematic processing of service data, wherein each column represents an attribute (such as temperature, humidity, charge and discharge depth, etc.) that has a significant influence on the storage electricity performance, and each row represents a record at a time point. By constructing such a time sequence matrix, the trends of various influencing factors over time and their correlations with each other can be clearly shown, providing a data basis for subsequent storage power unit life assessment.

[0025] The process of statistical storage electricity influence attribute time sequence matrix involves data cleaning, feature extraction, time series analysis and other data processing technologies, aiming to extract the most representative and predictive information from massive raw service data. Through the analysis method based on time sequence data, the limitations of traditional periodic detection are broken through, and the dynamic change characteristics of the storage power unit in the whole life cycle can be captured, which helps to discover potential quality risks.

[0026] S300: Statistics of storage power unit samples meeting the element type list and the element quantity list, working load time sequence information of the storage electricity influence attribute time sequence matrix.

[0027] Specifically, after obtaining the element type list and the element quantity list of the target storage power unit of the target new energy power station and constructing the storage electricity influence attribute time sequence matrix, the working load time sequence information of the storage power unit sample meeting the specific configuration condition is further counted, which provides basic information for the redundancy life assessment of the target storage power unit. By analyzing the storage power unit samples with similar configurations, the working load change rule in actual operation is obtained, which provides a reference basis for the life assessment of the target storage power unit.

[0028] Firstly, taking the element type list and the element quantity list of the target storage power unit as the screening condition, the storage power units with the same or highly similar element configuration are selected from the historical database or the online monitoring system as samples. This screening method based on element composition ensures the comparability of the selected samples and the target storage power unit in structure and performance characteristics, improves the pertinence and accuracy of the subsequent analysis results. Next, combined with the obtained storage electricity influence attribute time sequence matrix, the working load time sequence information of the selected storage power unit samples is statistically analyzed. The working load time sequence information refers to the actual load state of the storage power unit at different time points, reflecting the working performance of the unit under various environmental conditions and use scenarios. By statistically analyzing the working load time sequence of multiple similar configuration samples, the typical load mode and change trend of the specific type of storage power unit can be identified, providing more reliable data support for the subsequent redundancy life assessment.

[0029] Through statistical analysis based on actual operation data, the limitations of relying only on theoretical models or design parameters in traditional quality detection are broken through, and the performance state of the storage unit in the real working environment can be more comprehensively reflected, effectively improving the accuracy and predictability of quality detection.

[0030] S400: According to the workload time sequence information, the redundancy life of the target storage unit is evaluated, and a redundancy life prediction value is obtained.

[0031] Specifically, after obtaining the workload time sequence information, the redundancy life of the target storage unit is evaluated, and a redundancy life prediction value is obtained. The redundancy life refers to the remaining service life of the storage unit under the condition of maintaining normal working performance, which is an index for evaluating the quality state of the storage unit.

[0032] Based on the obtained workload time sequence information, combined with the design parameters and theoretical model of the storage unit, the future performance degradation trend of the target storage unit is modeled and analyzed through a specific life prediction algorithm. This prediction process not only considers the current state of the storage unit, but also fully integrates historical load variation rules and environmental influence factors, realizes dynamic evaluation of the redundancy life, and obtains the redundancy life prediction value. The redundancy life prediction value is a quantitative index, usually expressed in time units (such as days, months, years) or cycle times, reflecting the expected duration of the storage unit to continue normal operation under the current use mode and environmental conditions.

[0033] By introducing the redundancy life evaluation mechanism, the limitations of traditional periodic detection methods that cannot identify potential risks are broken through, and the forward-looking evaluation of the quality state of the storage unit is realized, providing a basis for timely discovering and handling quality problems, effectively improving the operation safety and stability of new energy power stations.

[0034] S500: When the redundancy life prediction value is less than or equal to the redundancy life threshold value, the target storage unit is temporarily marked for quality detection.

[0035] Specifically, after obtaining the redundancy life prediction value, quality detection decision is made according to the redundancy life prediction value. When the redundancy life prediction value is less than or equal to the pre-set redundancy life threshold value, the target storage unit will be temporarily marked for quality detection. The redundancy life threshold value is a critical value pre-set according to the type, operating environment and safety requirements of the storage unit, representing the life node that needs special attention of the storage unit.

[0036] The temporary quality detection mark is a high-priority detection arrangement mechanism, which is implemented for those energy storage units with low redundancy life prediction value and potential quality risks. Unlike traditional fixed-cycle detection, this temporary detection is dynamically triggered based on data analysis results, which can timely respond to potential risks caused by changes in energy storage unit performance. The temporary quality detection mark usually contains detection time, detection items, priority, etc. information, which is recorded in the power station management system and distributed to relevant maintenance personnel. This detection mark mechanism based on prediction results realizes the transition from periodic detection to predictive detection, significantly improving the pertinence and efficiency of quality detection.

[0037] Through the temporary quality detection mark, potential risks can be identified and intervened before serious quality problems occur in the energy storage unit, effectively avoiding safety hazards and economic losses caused by untimely detection, providing more reliable protection for the safe operation of new energy power stations. This proactive prevention detection strategy can effectively improve the overall operation stability of new energy power stations and prolong the service life of energy storage equipment.

[0038] S600: When the redundancy life prediction value is greater than the redundancy life threshold value, a default cycle quality detection mark is performed on the target energy storage unit.

[0039] Specifically, when the redundancy life prediction value is greater than the preset redundancy life threshold value, a default cycle quality detection mark is performed on the target energy storage unit, using a conventional detection frequency and detection scheme.

[0040] The default cycle quality detection mark is a regular detection arrangement for energy storage units in good condition and with sufficient expected service life. Unlike temporary quality detection, default cycle quality detection follows a pre-established detection plan and is performed at fixed time intervals, which can be quarterly, semi-annual, or annual detection, etc. The specific cycle can be flexibly set according to the type of energy storage unit and the operating environment. The default cycle quality detection mark also contains detection time, detection items, etc. information, but its priority is usually lower than that of temporary quality detection. This differentiated detection strategy realizes the rational allocation of detection resources, ensuring that potential risk energy storage units are given timely attention, while avoiding excessive detection of energy storage units in good condition, improving overall detection efficiency.

[0041] Through the comparison of the redundancy life prediction value and the redundancy life threshold value, the intelligent allocation of detection resources is realized, overcoming the limitations of traditional periodic detection methods. This adaptive detection mechanism based on data analysis not only improves the accuracy and efficiency of quality detection, but also reduces detection costs, realizes targeted quality detection mark of energy storage units, and effectively prevents the operation risks of energy storage units.

[0042] Further, the service data of the target energy storage unit of the target new energy power plant is called to count the energy storage influence attribute time sequence matrix, including:

[0043] S210: According to the energy storage type of the target energy storage unit, frequent mining is performed to obtain the first energy storage influence attribute to the Nth energy storage influence attribute;

[0044] S220: From the service data, extract the first energy storage influence attribute initial time sequence information for neighborhood hierarchical clustering analysis to obtain the first energy storage influence attribute time sequence information;

[0045] S230: Until the Nth energy storage influence attribute initial time sequence information is extracted from the service data for neighborhood hierarchical clustering analysis to obtain the Nth energy storage influence attribute time sequence information;

[0046] S240: According to the first energy storage influence attribute time sequence information to the Nth energy storage influence attribute time sequence information, the energy storage influence attribute time sequence matrix is constructed.

[0047] In a feasible implementation, in constructing the energy storage influence attribute time sequence matrix, first, according to the target energy storage type (such as lithium ion battery, sodium sulfur battery, super capacitor, etc.) of the target energy storage unit as the basic condition, targeted frequent mining is performed. Frequent mining is a data mining technology that identifies key attributes that have a significant impact on a specific energy storage type by statistically analyzing the association frequency between each attribute and the energy storage type. In this way, the most relevant attribute set can be selected from a large number of potential influencing factors, including from the first energy storage influence attribute to the Nth energy storage influence attribute. These selected influence attributes will become the core dimension of subsequent analysis, ensuring the pertinence and efficiency of data processing. After determining the influence attributes, the initial time sequence information related to the first energy storage influence attribute is extracted from the service data, which reflects the original value of the attribute at different time points. Then, the neighborhood hierarchical clustering analysis method is applied to these initial time sequence information, based on the time continuity and numerical similarity between data points, data points with similar change patterns are classified into the same category, thereby reducing noise interference and refining more representative time sequence patterns. After this processing, the first energy storage influence attribute time sequence information is obtained, which can more accurately reflect the law of the attribute changing with time.

[0048] Following the processing flow of S220, the same operation is performed on the second, third, and Nth energy storage impact attributes in turn. For each impact attribute, its initial timing information is extracted from the service data, and then optimized through neighborhood hierarchical clustering analysis, finally obtaining the timing information of the attribute. This sequential iteration processing mechanism ensures that all identified impact attributes can be systematically analyzed to form a complete timing information set. Then, all timing information from the first energy storage impact attribute timing information to the first energy storage impact attribute timing information is integrated into a structured timing matrix to form the energy storage impact attribute timing matrix. In this matrix, each column corresponds to an energy storage impact attribute, each row corresponds to a time point, and the matrix element represents the value of a specific impact attribute at a specific time point. This matrix data structure allows the timing changes of each impact attribute and their mutual correlation to be uniformly expressed, facilitating subsequent comprehensive analysis and providing necessary data support for subsequent workload statistics and redundancy life assessment.

[0049] Further, according to the energy storage type of the target energy storage unit, frequency mining is performed to obtain the first energy storage impact attribute to the Nth energy storage impact attribute, including:

[0050] S211: Obtain a set of impact attributes to be screened;

[0051] S212: Traverse the set of impact attributes to be screened and count a frequency set that appears together with the energy storage type;

[0052] S213: According to the frequency set, screen a first-level impact attribute set from the set of impact attributes to be screened, which is greater than or equal to a frequency threshold;

[0053] S214: Traverse the first-level impact attribute set to perform support evaluation and obtain a support set;

[0054] S215: According to the support set, screen the first energy storage impact attribute to the Nth energy storage impact attribute from the first-level impact attribute set, which is greater than or equal to a support threshold.

[0055] In a preferred embodiment, when performing frequent mining, first, a set of all attributes that can affect the performance of energy storage is obtained, i.e. a set of attributes to be screened. The set of attributes to be screened covers various factors that can affect the performance of energy storage units, such as ambient temperature, humidity, charging and discharging current, voltage fluctuation, cycle number, workload, etc. These attributes can come from various sources such as professional literature, equipment manuals, historical operation records, and expert experience. The obtained set of attributes to be screened is the basis for subsequent accurate screening, ensuring that the analysis process does not miss potential key influencing factors. After obtaining the set of attributes to be screened, each influencing attribute in the set of attributes to be screened is traversed to count its frequency of co-occurrence with a specific energy storage type. Specifically, a large number of operation records related to the energy storage type are extracted from the historical database, and the frequency of each influencing attribute appearing in these records and having a significant impact on the performance of the energy storage is analyzed. This statistical analysis is based on the principle of association rule mining, which can quantitatively describe the association strength between each attribute and the energy storage type, forming a frequency set. Each element in the set corresponds to an influencing attribute and its frequency, providing a numerical basis for subsequent screening.

[0056] Then, based on the obtained frequency set, a frequency threshold is introduced as a screening criterion to select attributes with a frequency value greater than or equal to the frequency threshold from the set of attributes to be screened, forming a set of primary influencing attributes. The frequency threshold is a pre-set critical value that can be flexibly adjusted according to actual application scenarios and precision requirements. Through this frequency-based preliminary screening mechanism, attributes with low correlation to the energy storage type can be effectively filtered out, leaving only the most relevant influencing factors. The set of primary influencing attributes is significantly smaller in size than the original set of attributes to be screened, but has more concentrated information value, laying the foundation for subsequent fine screening. Subsequently, the support of each attribute in the set of primary influencing attributes is evaluated. Support is a more accurate evaluation indicator than frequency, considering not only the frequency of attribute occurrence, but also the actual impact of attribute changes on the performance of energy storage. By analyzing historical data, the support value of each primary influencing attribute can be calculated, forming a support set. This support-based evaluation mechanism can more comprehensively reflect the actual importance of influencing attributes, avoiding the possible one-sidedness of relying solely on frequency. Then, based on the obtained support set, a support threshold is introduced as a second round of screening criterion to further select attributes with a support value greater than or equal to the support threshold from the set of primary influencing attributes, and finally determine the first energy storage influencing attribute to the Nth energy storage influencing attribute. These finally screened influencing attributes not only co-occur frequently with a specific energy storage type, but also have a significant actual impact on the performance of energy storage, and are the core dimensions for subsequent establishment of the time sequence matrix of energy storage influencing attributes.

[0057] Through the above two-stage screening mechanism, the most representative and predictive influence attribute set can be effectively identified, laying a foundation for accurately evaluating the redundant life of the energy storage unit.

[0058] Further, the support degree evaluation is performed on the first influence attribute set to obtain a support degree set, including:

[0059] S2141: Collecting a plurality of energy storage historical data of the energy storage type, wherein any one energy storage historical data includes a first influence attribute record value set and an energy storage amount record value;

[0060] S2142: Performing the same attribute deviation modulus calculation on the plurality of energy storage historical data to obtain a plurality of first influence attribute record value deviation sets and a plurality of energy storage amount record value deviations;

[0061] S2143: Obtaining a first influence attribute deviation threshold set;

[0062] S2144: From the plurality of first influence attribute record value deviation sets, extracting a plurality of first influence attribute record value deviations only having a first influence attribute deviation greater than a first influence attribute deviation threshold;

[0063] S2145: Based on the plurality of first influence attribute record value deviations, extracting a plurality of first influence attribute associated energy storage amount record value deviations from the plurality of energy storage amount record value deviations;

[0064] S2146: Calculating the ratio of the plurality of first influence attribute associated energy storage amount record value deviations and the plurality of first influence attribute record value deviations in one-to-one correspondence, and then performing the mode value statistics to obtain a first influence attribute support degree, which is added to the support degree set.

[0065] In a preferred embodiment, when obtaining the support set, first, a plurality of energy storage historical data related to the target energy storage type is collected from a historical database or an online monitoring system. These energy storage historical data have clear structural characteristics, and each energy storage historical data contains two parts of key information: a set of first-level influence attribute record values and an energy storage amount record value. Among them, the set of first-level influence attribute record values records the specific values of the screened first-level influence attributes at a certain time, such as environmental temperature 25°C, humidity 60%, charging current 5A, etc.; and the energy storage amount record value represents the actual energy storage state of the energy storage unit at the corresponding time, usually expressed in percentage of capacity or actual stored power units. This paired data structure containing causes (influence attributes) and results (energy storage amount) provides the necessary conditions for subsequent analysis of the correlation between each attribute and energy storage performance. After obtaining a plurality of energy storage historical data, the original plurality of energy storage historical data is converted into a more comparable deviation form through the same attribute deviation modulus calculation. Specifically, first, the reference values (such as average values or nominal values) of each attribute and energy storage amount are determined, then the deviations of each attribute value and energy storage amount value in each energy storage historical data from the corresponding reference values are calculated, and the absolute values (modulus values) are taken. After this processing, the original plurality of energy storage historical data is converted into a plurality of sets of first-level influence attribute record value deviations and a plurality of energy storage amount record value deviations. This deviation-based analysis method can more intuitively reflect the corresponding relationship between the changes of each influence attribute and the changes of the energy storage amount, eliminating the interference of the dimension and numerical range differences between different attributes, and improving the accuracy and comparability of subsequent analysis.

[0066] Then, a corresponding deviation threshold is set for each first-level influence attribute to form a set of first-level influence attribute deviation thresholds. These deviation thresholds are reference standards for judging whether the changes of each attribute are significant. Only when the attribute changes exceed a certain threshold, the changes are considered to have practical significance. The setting of the deviation threshold can be based on professional knowledge, equipment specifications or statistical analysis results, and different threshold standards can be used for different attributes. For example, ±5°C can be set as the deviation threshold for temperature, and ±10% can be set for humidity. By introducing these specialized threshold standards, changes in attributes that have small fluctuations and limited impact on energy storage performance can be effectively filtered out, focusing on analyzing key changes that have a significant impact. Subsequently, data screening is performed for the first influence attribute, and from the plurality of sets of first-level influence attribute record value deviations, records are extracted that only have the first influence attribute deviation greater than the corresponding threshold and the deviations of other attributes do not exceed their respective thresholds. This screening condition ensures that the first influence attribute is the only significant change factor in the selected records, eliminating the possibility of interference from other attributes, creating a pure data environment for subsequent analysis of the independent support of the first influence attribute. By controlling other variables to remain relatively stable, the influence of a single variable is highlighted, thereby achieving accurate evaluation of the support of each attribute.

[0067] On the basis of obtaining a plurality of first impact attribute record value deviations, further extract the energy storage deviations corresponding to the first impact attribute record value deviations from a plurality of energy storage record value deviations, called first impact attribute associated energy storage record value deviations. These paired deviation data establish a direct correspondence between the first impact attribute change and the energy storage change, providing basic data for calculating the support. The process of this association extraction ensures the accuracy of the causal correspondence, avoids the interference of irrelevant data, and improves the reliability of subsequent support calculation. Then, the ratio of each pair of first impact attribute record value deviation and its corresponding first impact attribute associated energy storage record value deviation is calculated. These ratios reflect the degree of energy storage change caused by unit attribute change, which is a direct quantitative expression of attribute impact strength. Then, the mode value statistics of all calculated ratios are performed, that is, the value with the highest frequency in these ratios is found, which is taken as the support of the first impact attribute and added to the support set. The statistical method of using mode instead of average as support can effectively reduce the interference of abnormal data and improve the stability and representativeness of support evaluation. This support calculation method based on ratio and mode realizes the accurate quantification of the importance of impact attribute and provides a basis for subsequent final screening.

[0068] Through the above steps, the support of the first impact attribute and even all primary impact attributes can be systematically evaluated, forming a complete support set and laying a foundation for finally determining the key impact attribute.

[0069] Further, the energy storage unit samples satisfying the element type list and the element quantity list are counted, and the working load time sequence information of the energy storage impact attribute time sequence matrix includes:

[0070] S310: Selecting an energy storage unit sample set with the element type list and the element quantity list as the unit size constraint;

[0071] S320: Collecting a plurality of working load time sequence record data of the energy storage unit sample set with energy storage as the working load index and the energy storage impact attribute time sequence matrix as the environmental constraint condition;

[0072] S330: Performing simultaneous load mode evaluation on the plurality of working load time sequence record data to obtain the working load time sequence information.

[0073] In a feasible implementation, first, the element model list and the element quantity list are taken as the unit set size constraint to select the sample set of the energy storage unit, so as to filter out the reference sample with similar configuration based on the element composition information of the target energy storage unit. Specifically, the element model list and the element quantity list obtained are taken as the unit set size constraint condition, and those energy storage units with high similarity in element composition are selected from the historical database or the online monitoring system to form the sample set of the energy storage unit. The filtering mechanism based on the element composition ensures the consistency of the selected sample and the target energy storage unit in physical structure and basic performance, and provides a reliable reference standard for subsequent load analysis. In actual operation, a certain degree of matching tolerance can be allowed, for example, the element quantity can be within ±5% range, or the functionally equivalent alternative model element is accepted, so as to increase the number of available samples and improve the stability of the statistical result. Through the sample filtering mechanism, the pertinence and reference value of the subsequent work load analysis can be ensured.

[0074] After determining the sample set of the energy storage unit, the work load data of the samples in actual operation is further collected. First, the energy storage capacity is selected as the core index of the work load, which directly reflects the actual energy storage state and use intensity of the energy storage unit. At the same time, the constructed time sequence matrix of the energy storage influence attribute is introduced as the environmental constraint condition, that is, the actual values of various influence attributes are considered when collecting the work load data, so as to ensure that the collected load data has clear environmental background information. Based on these settings, a plurality of work load time sequence record data is extracted from the operation records of the sample energy storage units, each work load time sequence record data contains a complete sequence of the energy storage capacity changing with time and corresponding environmental attribute information. This data collection method combined with environmental constraints ensures the comprehensiveness and environmental adaptability of the work load analysis, and provides more accurate data support for subsequent load statistics and life assessment.

[0075] Subsequently, representative work load time sequence information is extracted from the work load time sequence record data. Specifically, first, the plurality of work load time sequence record data collected is aligned by time point, and then the mode of the load value at each time point is evaluated, that is, the load level with the highest frequency at that time is found. This statistical method based on the mode rather than the mean value can effectively filter out the interference of abnormal data and extract the most representative work load mode. After this time sequence mode evaluation processing, the standardized work load time sequence information is obtained, which reflects the work load change rule of the energy storage unit with a specific configuration under typical environmental conditions, and provides a core reference basis for subsequent redundancy life assessment. Compared with single sample analysis, this multi-sample statistical method has higher stability and representativeness, can effectively reduce the influence of accidental factors, and improve the accuracy of redundancy life prediction.

[0076] Further, according to the workload time sequence information, the redundant life of the target energy storage unit is evaluated to obtain a redundant life prediction value, including:

[0077] S410: The workload time sequence information includes a first time domain workload to an Mth time domain workload.

[0078] S420: According to the first time domain workload and the rated life, the redundant life of the target energy storage unit is evaluated to obtain a first time domain redundant life prediction value.

[0079] S430: According to the second time domain workload and the first time domain redundant life prediction value, the redundant life of the target energy storage unit is evaluated to obtain a second time domain redundant life prediction value.

[0080] S440: Until the Mth time domain workload and the M-1th time domain redundant life prediction value, the redundant life of the target energy storage unit is evaluated to obtain a redundant life prediction value.

[0081] In a feasible implementation, the workload time sequence information includes a first time domain workload to an Mth time domain workload. For example, the obtained workload time sequence information is time domain divided, and continuous time sequence data is decomposed into a plurality of discrete time periods from the first time domain workload to the Mth time domain workload. The time domain division can adopt different division standards based on the operation characteristics of the energy storage unit, for example, can be divided according to natural time units (such as day, week, month), can also be divided according to the working cycle of the energy storage unit (such as the number of charge and discharge times), and can also be divided according to the change nodes of the storage impact attributes. The workload data in each time domain reflects the actual working state and use intensity of the energy storage unit in that specific time period. This time domain processing method enables the system to finely capture the dynamic characteristics of the change of the workload over time, laying a foundation for realizing high-precision sequential and gradual life evaluation.

[0082] Then, taking the rated life of the energy storage unit as the initial reference benchmark, combining the first time domain workload, and applying a specific life evaluation model, the redundant life prediction value of the energy storage unit at the end of the first time domain is calculated. The rated life is usually provided by the manufacturer and is the expected service life of the energy storage unit under standard working conditions and use mode. However, the actual working environment and load mode often differ greatly from the standard test conditions, and these differences will cause the actual life consumption rate of the energy storage unit to change. By comparing and analyzing the first time domain workload with the rated life, the actual life consumption of the energy storage unit in the first time domain stage can be evaluated, and the remaining life status at the end of the stage can be predicted. This evaluation method based on actual load breaks through the limitations of traditional time-based calculation and can more truly reflect the performance degradation process of the energy storage unit.

[0083] Subsequently, the progressive phase of the redundancy life assessment is entered. Unlike step S420, the initial rated life is no longer used as the reference here, but the first time-domain redundancy life prediction value calculated in step S420 is used as the new starting point, and the redundancy life prediction value at the end of the second time domain is calculated by combining the workload data of the second time domain, i.e., the second time-domain redundancy life prediction value. This progressive evaluation mechanism fully considers the cumulative effect and nonlinear characteristics of life consumption, and can accurately reflect the dynamic evolution process of the performance of the energy storage generator set with the change of use time and load. At the same time, since each evaluation is based on the latest redundancy life status and the actual load of the current time domain, it can sensitively capture the inflection point and abnormal fluctuation of the performance change of the energy storage generator set, and provide a basis for early warning of quality risks. According to the same evaluation principle, the workload data from the third time domain to the final Mth time domain is processed in turn. For each time domain, the redundancy life prediction value of the previous time domain is used as the evaluation starting point, and the latest redundancy life prediction value at the end of the time domain is calculated by combining the workload of the current time domain. Through this chain iteration evaluation method, the redundancy life prediction value at the end of the Mth time domain is obtained, i.e., the current redundancy life status of the target energy storage generator set.

[0084] Through multi-time domain progressive evaluation, the working state change and performance evolution trajectory of the energy storage generator set in the entire service process are fully considered, high-precision dynamic prediction of the redundancy life is realized, a basis is provided for subsequent quality detection decision, and the foresight and precision of new energy power station quality management are effectively improved.

[0085] Further, according to the first time domain workload and rated life, the redundancy life of the target energy storage generator set is evaluated to obtain a first time-domain redundancy life prediction value, comprising:

[0086] S421: Collecting a plurality of groups of data with the element type list and the element quantity list as constraints, wherein any one of the plurality of groups of data includes workload record data, initial life setting value record data, and a label identifying the redundancy life;

[0087] S422: Configuring a decision tree quantity threshold with the element type quantity as a constraint;

[0088] S423: Based on the decision tree quantity threshold, combining the plurality of groups of data to perform random forest training to obtain a redundancy life evaluator, and binding the redundancy life evaluator with the target energy storage generator set.

[0089] In a preferred embodiment, first, a list of element models and a list of element quantities of the target energy storage unit are used as screening conditions to collect multiple sets of data of energy storage units with similar configurations from the historical database. This screening mechanism based on element composition ensures the relevance and reference value of the collected data, providing a high-quality sample basis for subsequent model training. The collected multiple sets of data have a clear three-element structure: the working load record data reflect the load state changes of the energy storage unit during actual operation; the initial life setting value record data record the original design life parameters of each energy storage unit; and the label identifying the redundant life records the actual measured or empirically estimated remaining life value under specific load conditions. This complete data structure containing input features (working load and initial life) and output targets (redundant life) provides the necessary training samples for building the prediction model.

[0090] Then, the number of decision trees in the random forest model is configured based on the number of element models of the target energy storage unit. The number of decision trees is one of the core parameters of the random forest algorithm, directly affecting the complexity, generalization ability, and computational efficiency of the model. Generally, the more diverse the performance influencing factors of an energy storage unit with more types of elements and complex structure, the more decision trees are needed to capture these complex relationships. By dynamically configuring the decision tree parameters based on the number of element models, the model complexity is adaptively matched with the structure complexity of the energy storage unit, avoiding overfitting of the model for simple systems while ensuring the model's expressive ability for complex systems, improving the accuracy and applicability of redundant life evaluation.

[0091] Subsequently, based on the configured number of decision trees threshold, the collected multiple sets of data are used to apply the random forest algorithm for model training. Random forest is an ensemble learning method that can effectively handle high-dimensional features, nonlinear relationships, and noisy data by building multiple decision trees and taking their average prediction results, making it very suitable for performance prediction of complex systems such as energy storage units. During training, the working load record data and the initial life setting value record data are used as input features, and the label identifying the redundant life is used as the output target. Through iterative optimization, a redundant life evaluator with high prediction accuracy is finally obtained. The trained redundant life evaluator is bound to the specific target energy storage unit, rather than using a general model. This targeted model binding mechanism takes into account the individual differences of different energy storage units, achieving highly customized redundant life evaluation, significantly improving the accuracy and reliability of the prediction results, and providing a solid foundation for subsequent quality detection decisions.

[0092] After obtaining the redundancy life evaluator, progressive redundancy life prediction in steps S410 to S440 is implemented using the redundancy life evaluator. By binding the redundancy life evaluator with the target energy storage unit, the first time domain working load and rated life data can be input, and the first time domain redundancy life prediction value can be obtained; the second time domain working load and the redundancy life prediction value of the previous time domain are input, and the second time domain redundancy life prediction value is obtained; and so on, until the redundancy life prediction value is finally obtained. This progressive evaluation mechanism based on machine learning breaks through the limitations of the traditional linear decay model and can accurately capture the nonlinear performance changes of the energy storage unit in the whole life cycle, providing accurate and reliable data support for subsequent quality detection decisions.

[0093] Embodiment two, as shown in Figure 2 based on the same inventive concept as the quality management method of the new energy power station provided in embodiment one, the embodiment of the present application also provides a quality management system of a new energy power station, comprising:

[0094] The data receiving module 11 is configured to receive an element type list and an element quantity list of a target energy storage unit of a target new energy power station.

[0095] The service analysis module 12 is configured to call service data of the target energy storage unit of the target new energy power station and count a storage influence attribute time sequence matrix.

[0096] The load counting module 13 is configured to count energy storage unit samples satisfying the element type list and the element quantity list in working load time sequence information of the storage influence attribute time sequence matrix.

[0097] The life evaluation module 14 is configured to perform redundancy life evaluation on the target energy storage unit according to the working load time sequence information, and obtain a redundancy life prediction value.

[0098] The temporary inspection identification module 15 is configured to perform temporary quality detection identification on the target energy storage unit when the redundancy life prediction value is less than or equal to a redundancy life threshold value.

[0099] The default identification module 16 is configured to perform default periodic quality detection identification on the target energy storage unit when the redundancy life prediction value is greater than the redundancy life threshold value.

[0100] Further, the service analysis module 12 comprises the following execution steps:

[0101] According to the energy storage type of the target energy storage unit, frequent mining is performed to obtain a first storage influence attribute to an Nth storage influence attribute.

[0102] From the service data, extract the first storage power influence attribute initial time sequence information for neighborhood hierarchical clustering analysis to obtain the first storage power influence attribute time sequence information;

[0103] Until the Nth storage power influence attribute initial time sequence information is extracted from the service data for neighborhood hierarchical clustering analysis to obtain the Nth storage power influence attribute time sequence information;

[0104] According to the first storage power influence attribute time sequence information to the Nth storage power influence attribute time sequence information, the storage power influence attribute time sequence matrix is constructed.

[0105] Further, the service analysis module 12 further includes the following execution steps:

[0106] Obtain a set of to-be-screened influence attributes;

[0107] Iterate through the set of to-be-screened influence attributes to count a frequency set that appears together with the storage energy type;

[0108] According to the frequency set, screen a first-level influence attribute set from the set of to-be-screened influence attributes, which is greater than or equal to a frequency threshold value;

[0109] Iterate through the first-level influence attribute set to perform support evaluation to obtain a support set;

[0110] According to the support set, screen the first storage power influence attribute to the Nth storage power influence attribute from the first-level influence attribute set, which is greater than or equal to a support threshold value.

[0111] Further, the service analysis module 12 further includes the following execution steps:

[0112] Collect a plurality of storage energy historical data of the storage energy type, wherein any one storage energy historical data includes a first influence attribute record value set and a storage energy record value;

[0113] Perform same attribute deviation modulus calculation on the plurality of storage energy historical data to obtain a plurality of first influence attribute record value deviation sets and a plurality of storage energy record value deviations;

[0114] Obtain a first influence attribute deviation threshold value set;

[0115] From the plurality of first influence attribute record value deviations, extract a plurality of first influence attribute record value deviations that only have a first influence attribute deviation greater than a first influence attribute deviation threshold value;

[0116] Based on the plurality of first influence attribute record value deviations, extract a plurality of first influence attribute associated storage energy record value deviations from the plurality of storage energy record value deviations;

[0117] The ratio of the one-to-one corresponding multiple first influence attribute associated energy record value deviation and the multiple first influence attribute record value deviation is calculated, and the mode value statistics are performed to obtain the first influence attribute support degree, which is added to the support degree set.

[0118] Further, the load statistics module 13 includes the following execution steps:

[0119] The element model list and the element quantity list are taken as the unit set scale constraint to select a set of energy storage unit samples.

[0120] The energy storage capacity is taken as the working load index, and the energy storage influence attribute time sequence matrix is taken as the environmental constraint condition to collect a plurality of working load time sequence record data of the set of energy storage unit samples.

[0121] The plurality of working load time sequence record data is executed to obtain the working load time sequence information.

[0122] Further, the life evaluation module 14 includes the following execution steps:

[0123] The working load time sequence information includes a first time domain working load to an Mth time domain working load.

[0124] According to the first time domain working load and the rated life, the target energy storage unit is subjected to redundant life evaluation to obtain a first time domain redundant life prediction value.

[0125] According to the second time domain working load and the first time domain redundant life prediction value, the target energy storage unit is subjected to redundant life evaluation to obtain a second time domain redundant life prediction value.

[0126] Until the Mth time domain working load and the M-1th time domain redundant life prediction value are subjected to redundant life evaluation on the target energy storage unit to obtain the redundant life prediction value.

[0127] Further, the life evaluation module 14 further includes the following execution steps:

[0128] The element model list and the element quantity list are taken as the constraint to collect a plurality of groups of data, wherein any one of the plurality of groups of data includes working load record data, initial life setting value record data and label identifying redundant life.

[0129] The element model quantity is taken as the constraint to configure a decision tree number threshold.

[0130] Based on the decision tree number threshold, the plurality of groups of data are combined for random forest training to obtain a redundant life evaluator, and the redundant life evaluator is bound to the target energy storage unit.

[0131] It should be noted that the above-mentioned embodiments have been described by way of example only, and that modifications and additions can be made thereto without departing from the scope of the application.

[0132] Those skilled in the art will appreciate that embodiments of the application can be situated as methods, systems or computer program products. Accordingly, the application can take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the application can take the form of a computer program product on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROMs, optical storage devices, etc.) embodying computer readable program code.

[0133] The application is described with reference to the flowchart and / or block diagram illustrations of the methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each block of the flowchart and / or block diagrams, and combinations of blocks in the flowchart and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general purpose computer, special purpose computer, embedded computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart and / or block diagram block or blocks. Figure 1 one or more functions specified in the flowchart and / or block diagram block or blocks. Figure 1 means for carrying out each of the one or more functions specified in the flowchart and / or block diagram block or blocks.

[0134] These computer program instructions can also be stored in a computer- readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instructions which implement the flowchart and / or block diagram block or blocks. Figure 1 one or more functions specified in the flowchart and / or block diagram block or blocks. Figure 1 means for carrying out each of the one or more functions specified in the flowchart and / or block diagram block or blocks.

[0135] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the flowchart and / or block diagram block or blocks. Figure 1 one or more functions specified in the flowchart and / or block diagram block or blocks. Figure 1 means for carrying out each of the one or more functions specified in the flowchart and / or block diagram block or blocks.

[0136] Although preferred embodiments of the application have been described, additional modifications and changes can occur to others skilled in the art upon reading the preceding description.

[0137] It will be apparent to those skilled in the art that various modifications and variations can be made to the present application without departing from the spirit or scope of the application. Thus, it is intended that the present application cover modifications and variations of this application provided they come within the scope of the application and their equivalent technology.

Claims

1. A quality management method for a new energy power plant, characterized in that, include: Receive the component model list and component quantity list of the target energy storage unit of the target new energy power station; Retrieve the service data of the target energy storage units in the target new energy power plant, and statistically analyze the time series matrix of energy storage impact attributes, including: Based on the energy storage type of the target energy storage unit, perform frequent mining to obtain the first energy storage impact attribute up to the Nth energy storage impact attribute; From the service data, the initial time-series information of the first energy storage impact attribute is extracted and subjected to neighborhood hierarchical clustering analysis to obtain the time-series information of the first energy storage impact attribute. Until the service data is used to extract the initial time series information of the Nth energy storage impact attribute and perform neighborhood hierarchical clustering analysis, the time series information of the Nth energy storage impact attribute is obtained. Based on the time series information of the first energy storage impact attribute up to the time series information of the Nth energy storage impact attribute, construct the energy storage impact attribute time series matrix; The sample of energy storage units that meet the requirements of the component model list and the component quantity list is analyzed, and the workload time-series information of the energy storage impact attribute time-series matrix includes: Using the component model list and the component quantity list as constraints on the unit size, a sample set of energy storage units is selected; Using the energy storage capacity as the workload indicator and the time series matrix of the energy storage impact attributes as the environmental constraint, several workload time series records of the energy storage unit sample set are collected. Perform simultaneous load mode evaluation on the aforementioned workload time-series record data to obtain the workload time-series information; Based on the workload timing information, a redundancy lifetime assessment is performed on the target energy storage unit to obtain a predicted redundancy lifetime value, including: The workload timing information includes the first time-domain workload up to the Mth time-domain workload; Based on the first time-domain workload and rated life, the redundancy life of the target energy storage unit is evaluated to obtain the first time-domain redundancy life prediction value. Based on the second time-domain workload and the first time-domain redundancy lifetime prediction value, the redundancy lifetime of the target energy storage unit is evaluated to obtain the second time-domain redundancy lifetime prediction value. The redundancy lifetime of the target energy storage unit is evaluated based on the Mth time-domain workload and the M-1th time-domain redundancy lifetime prediction value to obtain the redundancy lifetime prediction value. When the predicted redundancy lifetime value is less than or equal to the redundancy lifetime threshold, the target energy storage unit is temporarily marked for quality inspection. When the predicted redundancy lifetime value is greater than the redundancy lifetime threshold, the target energy storage unit is marked with a default periodic quality inspection.

2. The method as described in claim 1, characterized in that, Based on the energy storage type of the target energy storage unit, frequent mining is performed to obtain the first energy storage impact attribute up to the Nth energy storage impact attribute, including: Obtain the set of influencing attributes to be filtered; Iterate through the set of influencing attributes to be screened and count the frequency set of attributes that co-occur with the energy storage type. Based on the frequency set, a set of first-level influence attributes that are greater than or equal to the frequency threshold is selected from the set of influence attributes to be screened; The support set is obtained by traversing the set of first-level influence attributes. Based on the support set, the first energy storage impact attribute that is greater than or equal to the support threshold is selected from the first-level impact attribute set up up to the Nth energy storage impact attribute.

3. The method as described in claim 2, characterized in that, The support set is obtained by traversing the set of primary influence attributes to perform support evaluation, including: Collect several historical energy storage data of the aforementioned energy storage type, wherein any one piece of historical energy storage data includes a set of primary influence attribute record values ​​and an energy storage record value; The same attribute deviation modulus is calculated for the aforementioned historical energy storage data to obtain multiple sets of deviations for primary influence attribute records and multiple deviations for energy storage records. Obtain the set of first-level influence attribute deviation thresholds; From the set of deviations of the multiple first-level influence attribute records, extract the deviations of multiple first-level influence attribute records where only the deviation of the first-level influence attribute is greater than the first-level influence attribute deviation threshold. Based on the deviations of the recorded values ​​of the multiple first influencing attributes, the deviations of the recorded values ​​of the multiple energy storage attributes are extracted from the deviations of the recorded values ​​of the multiple first influencing attributes; Calculate the ratio of the deviation of the energy storage record value associated with the multiple first influence attributes to the deviation of the record value of the multiple first influence attributes, then perform mode statistics to obtain the support of the first influence attributes, and add it to the support set.

4. The method as described in claim 1, characterized in that, Based on the first time-domain workload and rated lifespan, a redundancy lifetime assessment is performed on the target energy storage unit to obtain a first time-domain redundancy lifetime prediction value, including: Constrained by the component model list and the component quantity list, multiple sets of data are collected, wherein any one of the multiple sets of data includes workload record data, initial life set value record data and a tag identifying redundant life. Configure a threshold for the number of decision trees, using the number of component models as a constraint. Based on the threshold number of decision trees, a random forest is trained using the multiple sets of data to obtain a redundancy lifetime estimator, which is then bound to the target energy storage unit.

5. A quality management system for a new energy power plant, characterized in that, For implementing the method as described in any one of claims 1 to 4, comprising: The data receiving module is used to receive the component model list and component quantity list of the target energy storage unit of the target new energy power station; The service analysis module is used to retrieve the service data of the target energy storage units of the target new energy power station and to statistically analyze the time series matrix of energy storage impact attributes. The load statistics module is used to statistically analyze the working load time sequence information of the energy storage unit samples that meet the component model list and the component quantity list in the energy storage influence attribute time sequence matrix. The life assessment module is used to perform a redundancy life assessment on the target energy storage unit based on the workload timing information, and obtain a redundancy life prediction value. The temporary inspection identification module is used to temporarily identify the target energy storage unit when the predicted redundancy lifetime value is less than or equal to the redundancy lifetime threshold. The default identification module is used to perform a default periodic quality detection identification on the target energy storage unit when the predicted redundancy lifetime value is greater than the redundancy lifetime threshold.

Images