Intelligent analysis method and analysis system for new energy power station operation data

Abstract

This invention discloses an intelligent analysis method and system for operational data of new energy power plants, belonging to the field of data analysis. The method includes: real-time collection of operational data from the new energy power plant using various sensors; operational data includes the power generation of each power zone in the new energy power plant, the operating data of each individual cell in the energy storage battery pack, and environmental data; based on the operational data, determining monitoring parameters and indicator values, and using pre-set threshold ranges for each monitoring parameter and indicator value to monitor data from each power zone of the new energy power plant; using the operating data of each individual cell in the energy storage battery pack, environmental data, and the energy storage battery pack model to predict the health status of each energy storage battery pack; based on the data monitoring results and prediction results, issuing alarms and early warning information to operation and maintenance personnel for fault detection and repair. This solution can effectively improve the automation and accuracy of new energy power plant operation and reduce the operational labor costs of new energy power plants.

Description

Technical Field

[0001] The present invention relates to the technical field of data analysis, and in particular to a method and system for intelligently analyzing operating data of a new energy power station. Background Art

[0002] New energy is an important pillar of the future sustainable energy system and will gradually replace traditional petrochemical energy and occupy a dominant position.

[0003] However, compared with traditional power stations, renewable energy power supply is not as stable as traditional power supply, so more monitoring personnel are needed to ensure the normal operation of renewable energy power stations. In order to reduce the labor intensity of monitoring personnel, it is necessary to improve the degree of automation of renewable energy power stations to improve the intelligent operation management and monitoring intensity of renewable energy power stations.

[0004] Therefore, there is an urgent need for an intelligent analysis method and analysis system for new energy power station operation data. Summary of the invention

[0005] In order to solve the problem that the existing new energy power station operation has a low degree of automation and requires high manpower costs, an embodiment of the present invention provides a new energy power station operation data intelligent analysis method and analysis system.

[0006] On the one hand, a method for intelligent analysis of operation data of a new energy power station is provided, the method comprising:

[0007] Using various sensors to collect the operating data of the new energy power station in real time; wherein the operating data includes the power generation of each power zone in the new energy power station, the operating data of each single cell of the energy storage battery group and the environmental data;

[0008] Based on the operation data, determine monitoring parameters and indicator values, and use the preset threshold ranges of each monitoring parameter and each indicator value to perform real-time data monitoring of each power area of ​​the new energy power station;

[0009] Predicting the health status of each energy storage battery pack by using the operating data of each single battery of the energy storage battery pack, the environmental data and a pre-built energy storage battery pack model;

[0010] Based on the data monitoring and prediction results, alarms and early warning information are sent to operation and maintenance personnel to perform fault detection and repair.

[0011] On the other hand, a new energy power station operation data intelligent analysis system is provided, which is used to implement the method described in any embodiment of the specification, and the system includes:

[0012] A collection module is used to collect the operation data of the new energy power station in real time using various sensors; wherein the operation data includes the power generation of each power area in the new energy power station, the operation data of each single cell of the energy storage battery group, and the environmental data;

[0013] A monitoring module, for determining monitoring parameters and index values ​​based on the operation data, and performing real-time data monitoring of each power area of ​​the new energy power station by using the preset threshold ranges of each monitoring parameter and each index value;

[0014] A prediction module is used to predict the health status of each energy storage battery pack by using the operation data and environmental data of each single battery of the energy storage battery pack and a pre-built energy storage battery pack model;

[0015] The alarm module is used to send alarm and early warning information to operation and maintenance personnel based on data monitoring results and prediction results to perform fault detection and repair.

[0016] On the other hand, a computer device is provided, which includes a memory and a processor, wherein the memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory to implement the steps of the above-mentioned method.

[0017] On the other hand, a computer-readable storage medium is provided, wherein a computer program is stored in the storage medium, and when the computer program is executed by a processor, the steps of the above-mentioned method are implemented.

[0018] On the other hand, a computer program product is provided, comprising a computer program, wherein the computer program implements the steps of the above method when executed by a processor.

[0019] The technical solution provided by the present invention can at least bring the following beneficial effects:

[0020] By collecting the operating data of the new energy power station in real time, the monitoring parameters and indicator values ​​are calculated in real time, so as to monitor these monitoring parameters and indicator values ​​in real time according to the threshold range; at the same time, the pre-built energy storage battery pack model is used to simulate and predict the health status of each energy storage battery pack based on the real-time operating data and environmental data of each single battery of the energy storage battery pack; therefore, this solution can not only monitor the operation of the new energy power station in real time, but also predict the health status of the energy storage battery pack in the future, which can effectively improve the automation and accuracy of the operation of the new energy power station and reduce the operating manpower cost of the new energy power station. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0022] Figure 1 This is a flow chart of a method for intelligent analysis of operating data of a new energy power station provided by an embodiment of the present invention;

[0023] Figure 2 This is a structural diagram of a new energy power station operation data intelligent analysis system provided by an embodiment of the present invention;

[0024] Figure 3 It is a hardware architecture diagram of a computer device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0025] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0026] The specific implementation of the above concept is described below.

[0027] Please refer to Figure 1 , an embodiment of the present invention provides a method for intelligent analysis of operation data of a new energy power station, the method comprising:

[0028] Step 100, using various sensors to collect the operation data of the new energy power station in real time; wherein the operation data includes the power generation of each power area in the new energy power station, the operation data of each single cell of the energy storage battery group, and the environmental data;

[0029] Step 102, based on the operation data, determine the monitoring parameters and index values, and use the preset threshold ranges of the monitoring parameters and index values ​​to perform real-time data monitoring on each power area of ​​the new energy power station;

[0030] Step 104, predicting the health status of each energy storage battery pack by using the operation data and environmental data of each single battery of the energy storage battery pack and a pre-built energy storage battery pack model;

[0031] Step 106, based on the data monitoring results and prediction results, alarm and warning information are sent to the operation and maintenance personnel to perform fault detection and fault repair.

[0032] In the embodiment of the present invention, the operation data of the new energy power station is collected in real time, and the monitoring parameters and indicator values ​​are calculated in real time, so as to monitor these monitoring parameters and indicator values ​​in real time according to the threshold range; at the same time, a pre-constructed energy storage battery group model is used to simulate and predict the health status of each energy storage battery group based on the real-time operation data and environmental data of each single battery of the energy storage battery group; therefore, this solution can not only monitor the operation status of the new energy power station in real time, but also predict the health status of the energy storage battery group in the future, which can effectively improve the automation and accuracy of the operation of the new energy power station and reduce the operating manpower cost of the new energy power station.

[0033] Described below Figure 1 How the various steps are performed.

[0034] For step 100:

[0035] In this embodiment, for the convenience of management, the new energy power station can be divided into multiple power zones for zone management and operation. It can be understood that each power zone has several energy storage battery groups, and each energy storage battery group is composed of several single cells connected in series and parallel.

[0036] In this embodiment, the sensors may include voltage sensors, current sensors, temperature sensors, wind monitors and power meters, etc. The voltage sensors and current sensors can collect the voltage and current of each single cell of the energy storage battery pack, and can also be used to monitor the operating status of equipment such as photovoltaic areas, warehouses, and energy storage areas in the power station. The temperature sensor can collect the ambient temperature of each location in the entire power station, and can also collect the operating temperature of all equipment including each single cell of the energy storage battery pack to avoid excessive temperature of the equipment. The wind monitor is used to collect wind power, and the power meter is used to collect the power generation and power consumption of each power area in the new energy power station.

[0037] Regarding step 102:

[0038] In this embodiment, the monitoring parameters may be equipment temperature, power generation, etc., which are set according to the actual situation. The index values ​​may be indicators such as power station energy storage loss rate, power occupancy rate, failure rate, power station utilization coefficient, etc., which may be set according to the actual situation. The monitoring parameters and index values ​​are monitored by setting the corresponding threshold range.

[0039] Regarding step 104:

[0040] In some embodiments, the energy storage battery model is created using the Modelica language, and step 104 may include:

[0041] For each energy storage battery pack, execute:

[0042] Inputting the operating data of each single cell of the energy storage battery group into the corresponding energy storage battery group model to update the setting parameter values ​​of each single cell model in the energy storage battery group model accordingly;

[0043] The simulation scenario parameters are set according to the environmental data, so that the energy storage battery pack model runs under the current simulation scenario parameters, and the inconsistent capacity decay and thermal runaway of the energy storage battery pack are predicted.

[0044] Existing simulation models are mainly established using traditional modeling and simulation platforms such as Matlab and Simulink. Simulink and other simulation platforms are based on mathematical modeling to establish various equivalent models to perform parameter identification and high-precision calculations on the models. In some simulations with high precision requirements, it is also necessary to design and calculate high-order equivalent circuit models. The entire modeling and simulation process requires the construction of mathematical models for different single cells. The modeling and simulation process is relatively cumbersome, and it is difficult for newcomers in the research field to learn and has a high threshold for use. In addition, existing battery management methods focus more on thermal runaway monitoring, and rarely monitor and predict the inconsistency of each single cell, resulting in the life and safety of the battery system not being effectively guaranteed.

[0045] The Modelica language environment has the characteristics of non-causal modeling. Using the Modelica language to establish a battery system model is a simulation model based on physical modeling. It is more intuitive and easy to understand in form, more in line with the researchers' intuitive understanding of the model, and more convenient for modifying and adjusting the various parameters of the model. Compared with traditional mathematical modeling methods, it can simplify the complex adjustments of model parameters that may occur during the research process, improve the efficiency of simulation calculations, and its simulation results are more in line with the experimental results of actual physical circuits.

[0046] Therefore, this embodiment inputs the real-time operating data of each single cell of the energy storage battery pack into the energy storage battery pack model created in advance using the Modelica language, and runs the energy storage battery pack model according to the current actual environmental data, so as to evaluate and predict the inconsistent capacity degradation and thermal runaway of each energy storage battery pack.

[0047] In some implementations, an optimization period is also set. In each optimization time period, each energy storage battery group model is optimized in the following manner:

[0048] The target parameters in the battery system model are optimized by using the real-time operating data of each single battery in the energy storage battery pack at each moment in the current optimization time period and the energy storage battery pack model at the historical moment to predict the results at each moment in the current optimization time period.

[0049] In this embodiment, since the energy storage battery pack will encounter many unknown and complex situations during the actual operation, in order to improve the simulation accuracy, an optimization cycle is also set to periodically optimize the target parameters in the energy storage battery pack model based on the real-time operation data of each single cell and the prediction results of the energy storage battery pack model. Therefore, this solution uses the Modelica language to establish an energy storage battery pack model, which can simplify the model building process, lower the learning and use threshold, improve the simulation efficiency, and can monitor and predict the inconsistency of each single cell, which can improve the comprehensiveness and accuracy of the prediction results.

[0050] In some embodiments, the step of "optimizing the target parameters in the battery system model by using the real-time operating data of each single battery in the energy storage battery pack at each moment in the current optimization time period and the energy storage battery pack model at the historical moment to predict the results at each moment in the current optimization time period" may include:

[0051] Based on the real-time operation data of each single battery in the energy storage battery group at each moment in the current optimization time period and the prediction results of the energy storage battery group model at the historical moment for the corresponding moment in the current optimization time period, the accuracy of the prediction results at each moment in the current optimization time period is scored;

[0052] Determine the fitness function based on the accuracy score results at each moment in the current optimization time period;

[0053] The target parameters to be optimized in the energy storage battery model are used to construct the positions and velocities of particles in the particle swarm-simulated annealing algorithm, and the initial annealing temperature and the final annealing temperature are determined;

[0054] In each optimization cycle when the annealing temperature is less than the final annealing temperature, the following are performed: the speed and position of each particle in the particle group are updated, and the fitness function value of each particle after the update is calculated based on the fitness function, so as to determine whether the new position is acceptable based on the fitness function value of each particle after the update and the fitness function value of each particle before the update, and then the annealing temperature is updated;

[0055] When the annealing temperature is greater than or equal to the final annealing temperature, the optimal solution is determined, and the optimization of the target parameters in the energy storage battery pack model is completed.

[0056] It should be noted that due to the long service life of the energy storage battery pack, some fixed parameters in the energy storage battery pack model may become invalid, and the target parameters need to be optimized at regular intervals to make the energy storage battery pack model effective and accurate throughout the life cycle of the target energy storage battery pack. This optimization period can be three months, six months or one year.

[0057] In this embodiment, since the energy storage battery pack model at a historical moment can predict the capacity decay, temperature, etc. (used to evaluate the health status) of each single battery in the target energy storage battery pack in a period of time in the future, and in each optimization time period, the real-time operation data of each single battery in the target energy storage battery pack at each moment can be obtained in real time, based on the difference between the real-time operation data and the prediction results at each moment in the current optimization time period, the target parameters in the energy storage battery pack model can be optimized.

[0058] Specifically, the accuracy scoring method of the prediction results at each moment in the current optimization time period is:

[0059] For each moment in the current optimization period, execute:

[0060] Calculate the difference between the actual SOC change rate and the predicted SOC change rate of each single battery at the current moment, determine the number of single batteries whose difference is greater than a first preset threshold, and assign scores based on the number of single batteries whose difference is greater than the first preset threshold;

[0061] Calculate the difference between the actual temperature and the predicted temperature of each single cell at the current moment, determine the number of single cells whose difference is greater than the second preset threshold, and give corresponding scores based on the number of single cells whose difference is greater than the second preset threshold to obtain the accuracy score result at the current moment within the current optimization time period.

[0062] In this embodiment, assuming that the number of single cells whose difference is greater than the first preset threshold is 2, 2 points can be given, and the number of single cells whose difference is greater than the second preset threshold is 3, 3 points can also be given directly. The scoring strategy can be set, which is not described in detail here.

[0063] Based on the accuracy score results at each moment in the current optimization time period, determine the fitness function:

[0064]

[0065] In the formula, N represents the total number of single cells in the target energy storage battery pack, score t,i Represents the accuracy score result of the i-th single cell at the t-th time in the current optimization time period, score avg Represents the comprehensive accuracy score. The smaller the value, the better the accuracy of the algorithm.

[0066] In this step, the initial annealing temperature is determined by the following formula:

[0067]

[0068] The final annealing temperature is determined by the following formula:

[0069]

[0070] Where χ1 and χ2 are the factors that determine the initial annealing temperature and the final annealing temperature, respectively, and π0 is {f(x i )-f(x i-1 )}, π n is {f(x i )-f(x i-1 )}, where f is the cooling rate function, x i-1 is the position of the particle in the previous iteration, x i The position of the particle in this iteration.

[0071] The speed and position of each particle in the particle swarm are updated by the following formula:

[0072]

[0073] In the formula, is the velocity of particle i in dimension d at time t; is the position of particle i in dimension d at time t, w is the inertia weight, which is used to control the continuity of particle velocity, c1 and c2 are learning factors, which are used to adjust the particle to the optimal position of the individual and the global optimal position Move, r1, r2 are random numbers between 0 and 1, used to increase the randomness of the search.

[0074] The acceptance of the new position is determined as follows:

[0075] P(ΔE,T (t) )=exp(-ΔE / (k·T (t) ))

[0076] Where, T (t) is the temperature at time t, ΔE is the difference in fitness between the new position and the position before the update, k is the Boltzmann constant, P(ΔE,T (t) ) is the probability of accepting a solution with poor fitness at temperature T.

[0077] Update annealing temperature by:

[0078] T (t+1) =α·T (t)

[0079] Where, T (t+1) is the temperature at time t+1, T (t) is the temperature at time t, and α is the cooling rate, which takes values ​​between 0 and 1.

[0080] Next, the construction process of the energy storage battery pack model is described in detail.

[0081] In some embodiments, the energy storage battery pack model is created by:

[0082] S1, using the model components in the Modelica model library to build a single cell battery model, and setting default parameter values ​​in the single cell battery model; wherein the parameters at least include cell electrical parameters and thermal related parameters, and the single cell battery model at least contains a battery pack, a signal transmission unit and a thermal model unit, and the thermal model unit is used to predict the temperature change of the single cell battery under different scenario parameters;

[0083] S2, using the Model class to arrange the positions of multiple single-cell battery models and connect them in series and parallel to form an energy storage battery pack model;

[0084] S3, based on the preset parameters of each single cell model in the inconsistency simulation experiment, adjusting the parameter value of each single cell model in the energy storage battery pack model, so as to simulate and run the energy storage battery pack model under different scenario parameters, and determine the inconsistency simulation result of the energy storage battery pack;

[0085] S4, comparing the inconsistency simulation results with the actual experimental results of the energy storage battery pack, and iterating and modifying the energy storage battery pack model and parameters based on the comparison results until an energy storage battery pack model that meets expectations is obtained.

[0086] In this embodiment, the Modelica language is used to first establish a single battery pack model and set the single battery parameters for packaging, and then the packaged single battery models are combined into a complete energy storage battery pack model. The parameters of each single battery pack model are modified based on the initial parameter differences of each single battery and the differences in thermal related parameters caused by different locations and environments, so as to introduce inconsistency-related factors. Since the Modelica language environment has the characteristics of non-causal modeling, it is a simulation model based on physical modeling, which is more intuitive and easy to understand in form, more in line with the researchers' intuitive understanding of the model, and more convenient for the modification and adjustment of each parameter of the model. Compared with the traditional mathematical modeling method, the physical modeling method based on the Modelica language in this embodiment simplifies the complex adjustment of model parameters that may occur during the research process, and the simulation calculation efficiency is higher, and its simulation results are more in line with the experimental results of the actual physical circuit. And the C code generated after the simulation compilation is completed on the target platform can be executed on different platforms, which improves the compatibility and universal applicability of the model and code. Therefore, this simulation method can not only simplify the model building process and reduce the threshold for learning and use, but also reduce the difficulty of simulation and improve the efficiency of simulation.

[0087] In some embodiments, step S1 may include:

[0088] Call the cell model in the Modelica model library, and set the cell electrical parameters and thermal related parameters in the electrical subunit and thermal subunit of the cell model respectively;

[0089] Call the battery module model in the Modelica model library to generate a battery pack using multiple battery cell models;

[0090] A signal transmission unit is formed by using a signal receiver and a ground pin, and a signal interface is provided for the signal transmission unit;

[0091] Establishing a thermal model unit and providing a thermal conversion interface for connecting to a battery pack;

[0092] Connect the battery pack, signal transmission unit and thermal model unit, and set the positive and negative electrode interfaces;

[0093] Use the Block class to encapsulate the battery pack, signal transmission unit, and thermal model unit to obtain a single battery model.

[0094] In an embodiment of the present invention, the battery cell electrical parameters include at least: SOC starting value, maximum capacity, OCV coefficient and power supply internal resistance coefficient; the thermal related parameters include at least: battery cell starting temperature, thermal conductivity between the battery cell and the shell, and module shell temperature.

[0095] In this embodiment, the model library includes battery cell models, battery module models, battery pack models, etc. The battery cell model in the Modelica model library is first called, and the battery cell electrical parameters and thermal related parameters are respectively set in the electrical subunit and thermal subunit of the battery cell model. Then, the battery module model in the Modelica model library is called to generate a battery pack using multiple battery cell models; a signal transmission unit is composed of a signal receiver and a ground pin, and a signal interface is set for the signal transmission unit; finally, a thermal model unit is established, and a thermal conversion interface for connecting to the battery pack is set, and then the battery pack, the signal transmission unit and the thermal model unit are connected, and the positive and negative electrode interfaces are set, then the battery pack, the signal transmission unit and the thermal model unit are encapsulated using the Block class to obtain a single battery model.

[0096] In some embodiments, the thermal model unit predicts the temperature change of the single battery under different scenario parameters in the following manner:

[0097] Get the ambient temperature in the current scene parameters to calculate the conduction heat loss and convection heat loss, and get the total heat loss equation;

[0098] Get the current voltage and current of the battery pack and calculate the heat generation;

[0099] A heat balance equation is constructed based on the total heat loss equation and heat generation to calculate the current temperature of the single cell.

[0100] In this embodiment, each single cell in the energy storage battery pack generates heat during the operation process due to the electrochemical reaction and the Joule heat caused by the resistance inside the battery during the charge and discharge process, which causes the operating temperature of the single cell to rise continuously. The temperature of the single cell will affect its electrochemical performance, and the operation of the single cell at high temperature will accelerate aging and shorten the service life. In addition, different cell electrical parameters and heat-related parameters will also cause different temperatures. Therefore, the thermal reaction of the single cell is closely related to the inconsistency of the battery. Therefore, in order to simulate the inconsistency of each single cell more accurately, when constructing a single cell model, a thermal model unit needs to be established in the single cell model. By setting a thermal conversion interface for the battery pack and connecting it to the thermal model unit, the thermal model part of the single cell is simulated and tested, so that the thermal model unit can predict the temperature changes of each single cell model under different operating conditions based on the inconsistency parameters of each single cell model, thereby realizing accurate simulation and prevention of thermal runaway and inconsistency.

[0101] In some embodiments, the real-time temperature of the single cell during operation is calculated by the following formula:

[0102]

[0103] In the formula,

[0104]

[0105] Where ρ is the density, C p is the specific heat capacity, V is the volume of the single cell, T is the current temperature of the single cell, Q gen is the heat generation, Q loss is the total amount of heat loss, I is the current, V is the current voltage, Q conv is the convective heat loss, Q cond is the conduction heat loss, h is the convective heat transfer coefficient, A is the surface area of ​​the single cell, T amb is the ambient temperature and k is the thermal conductivity.

[0106] In this embodiment, the thermal model unit takes into account the heat generated by the battery during the charging and discharging process, as well as the heat dissipated through different pathways, including convection and conduction. The thermal model of the battery includes a variety of heat transfer mechanisms, taking into full account the electrochemical reactions, material properties, geometric structures, and external environmental conditions inside the battery. The above formula can be used to predict the temperature distribution of each single cell, thereby optimizing the thermal management system of the battery to ensure that the battery operates within a safe operating temperature range. Therefore, in the process of modeling the energy storage battery pack, this embodiment models the heat conversion part of the model according to the principle of the thermal model to ensure accurate simulation of the operating environment of the battery.

[0107] After the single-cell battery model is established, a new Model class is created in Modelica. According to the structure and organizational connection method of the battery pack required for the study, the single-cell battery models are reasonably arranged and connected in series and parallel. The signal transmission unit and thermal model unit in each single-cell battery model are connected through the defined interfaces to form a complete data flow and input and output signals to obtain a complete energy storage battery pack model.

[0108] In some embodiments, step S3 comprises:

[0109] Based on the preset parameters of each single cell in the inconsistency simulation experiment, the SOC starting value, OCV coefficient, power supply internal resistance coefficient of each single cell model in the energy storage battery pack model, the difference in the starting temperature of the battery cell caused by the different location and environment of the single cell pack, and the difference in the thermal conductivity coefficient between the battery cell and the shell caused by the different location of the single cell pack are adjusted.

[0110] In this embodiment, in order to study the inconsistency problem of the energy storage battery pack, on the basis of using the same single cell model, inconsistency related factors are introduced, based on the differences in initial parameters of different single cells (SOC starting value and OCV coefficient, power supply internal resistance coefficient), and the differences in the starting temperature of the battery cell caused by the different locations and environments, and the differences in heat dissipation conditions caused by the different locations of the single cells (heat transfer coefficient between the battery cell and the casing), the battery cell electrical parameters and thermal related parameters in each single cell model are modified, and the model parameters of each single cell are modified through related factors to establish an energy storage battery pack model that can reflect the inconsistency of the energy storage battery pack.

[0111] After the energy storage battery pack parameters are set, the simulation scenario parameters are set, and the external environment parameters, such as the charge and discharge rate, operating environment temperature, etc., are set according to the scenarios required for the simulation, so as to simulate and run the energy storage battery pack model under different scenario parameters. When the energy storage battery pack model is simulated and run under different scenario parameters, the changes in the parameters of each single battery model in the energy storage battery pack model are observed and analyzed, and the results are compared and observed. The inconsistency of the energy storage battery pack shown by each battery cell in the energy storage battery pack model when running under different scenarios, for example, whether there are differences in the rate of change of the SOC of different single battery packs during operation, and the impact of these parameter differences on the performance of the entire battery pack, determine the inconsistency simulation results of the energy storage battery pack.

[0112] Afterwards, the inconsistency simulation results are compared with the actual experimental results of the energy storage battery pack, so that the energy storage battery pack model and parameters are modified and iterated based on the comparison results until an energy storage battery pack model that meets expectations is obtained.

[0113] In this embodiment, after the simulation is completed, the final analysis results are compared with the results of the actual energy storage battery group experiment to verify the accuracy and effectiveness of the established model and the set inconsistency conditions. After the verification results, the model and parameters are modified and iterated so that the established model can more effectively reflect the actual operating conditions of the energy storage battery group.

[0114] The above is the process of establishing the energy storage battery pack model. Since the target energy storage battery pack is always affected by harsh operating conditions, harsh seasonal environment and accidental manufacturing defects during actual use, the performance of each single battery will be accelerated to degrade or even thermal runaway. The complexity and suddenness of the use environment will cause deviations in the simulation effect of the energy storage battery pack model. Therefore, it is necessary to determine the setting parameters in the energy storage battery pack model. These setting parameters can be determined based on the operating data of each single battery in the target energy storage battery pack, such as the initial voltage, initial current, initial SOC, initial module shell temperature, etc. of each single battery. According to the real-time acquired operating data of each single battery in the target energy storage battery pack, the setting parameter values ​​of each single battery model in the energy storage battery pack model can be updated accordingly to improve the simulation prediction accuracy.

[0115] Regarding step 106:

[0116] In some embodiments, it further comprises:

[0117] Conduct life assessment on each component in the new energy power station, and classify each component into youth, middle-age and old age based on the usage time and the standard service life of the component, so as to set different inspection frequencies for components in different life stages, and remind operation and maintenance personnel to conduct inspections according to the corresponding inspection frequencies.

[0118] Then, step 106 may include:

[0119] When the value of a monitoring parameter or indicator exceeds the corresponding threshold range, an alarm message is sent to the operation and maintenance personnel, and the power zone information and component information related to the abnormal monitoring parameter or abnormal indicator are attached, so that the operation and maintenance personnel can perform fault troubleshooting and fault repair according to the order of the life cycle of the relevant components;

[0120] When the prediction result is abnormal, an early warning message is sent to the operation and maintenance personnel, and the location information and predicted status of the abnormal energy storage battery group are attached, so that the operation and maintenance personnel can prevent faults of the abnormal energy storage battery group.

[0121] In this embodiment, if the real-time monitoring result is abnormal, the operation and maintenance personnel need to repair it as soon as possible, while if the prediction result is abnormal, the operation and maintenance personnel can be warned and adjusted in time to prevent failures. When the real-time monitoring result is abnormal, the operation and maintenance personnel can prioritize the parts with longer service life according to the order of the life cycle of the relevant parts, so as to improve the troubleshooting and fault repair speed of the operation and maintenance personnel.

[0122] In some implementations, after step 106, the method further includes:

[0123] When at least one power zone fails to generate electricity, the required power generation of the faulty power zone is distributed to the remaining normal power zones based on the predicted failure coefficients and historical failure rates of the remaining normal power zones.

[0124] In this embodiment, the new energy power station has a total power generation index, and each power area has a fixed power generation capacity every day or every week. Assuming that the power generation capacity can be completed by working for 6 hours every day, when one of the power areas fails and cannot generate electricity, it is necessary to allocate the power generation capacity of the power area on that day to the remaining normal power areas. For example, the power generation capacity is evenly divided among the remaining normal power areas, so that the remaining normal power areas extend their working time every day. However, a simple equal division may accelerate the failure of the power area in poor condition. In order to avoid the possibility of accelerated failure of the normal power area, the power generation capacity can be reasonably allocated to the remaining normal power areas based on the predicted failure coefficient and historical failure rate of each normal power area.

[0125] Specifically, when at least one power zone fails to generate electricity, the power generation capacity of the faulty power zone is allocated to the remaining normal power zones based on the predicted fault coefficients and historical fault rates of the remaining normal power zones, including:

[0126] Sort the normal power areas in descending order based on the predicted fault coefficient of each normal power area;

[0127] Allocate the required power generation capacity of the faulty power zone to each normal power zone in sequence. For each normal power zone, perform the following:

[0128] B1, based on the current amount of electricity to be distributed divided by the number of normal power areas that are not currently distributed, determine the current amount of electricity to be distributed equally;

[0129] B2, allocate the current normal power area based on the current equally shared power, the predicted failure coefficient of the current normal power area and the historical failure rate;

[0130] B3, subtract the current allocation amount of the normal power zone from the amount of electricity to be distributed to obtain a new amount of electricity to be distributed, so as to jump to step B1 to distribute electricity to the next normal power zone.

[0131] Specifically, the current normal power area can be allocated in the following ways:

[0132] ΔD=(1-bl)D

[0133] Where ΔD is the current power distribution in the normal power area, b is the predicted fault coefficient, l is the historical fault rate, and D is the current equally divided power.

[0134] It can be understood that the predicted failure coefficient is determined based on the simulation prediction results of the energy storage battery group model. The higher the predicted failure coefficient, the worse the power station state is. Therefore, by using the above formula, the power distribution is reduced on the basis of equally dividing the power. The lower the predicted failure coefficient, the last one to be distributed to bear more remaining undistributed power.

[0135] Please refer to Figure 2 The embodiment of the present invention provides a new energy power station operation data intelligent analysis system, which is used to implement the method of any embodiment of the specification, and the system includes:

[0136] The acquisition module 201 is used to collect the operation data of the new energy power station in real time using various sensors; wherein the operation data includes the power generation of each power area in the new energy power station, the operation data of each single cell of the energy storage battery group, and the environmental data;

[0137] The monitoring module 202 is used to determine monitoring parameters and index values ​​based on the operation data, and to perform real-time data monitoring of each power area of ​​the new energy power station using the preset threshold ranges of each monitoring parameter and each index value;

[0138] The prediction module 203 is used to predict the health status of each energy storage battery group by using the operation data and environmental data of each single battery of the energy storage battery group and the pre-built energy storage battery group model;

[0139] The alarm module 204 is used to send alarm and warning information to the operation and maintenance personnel based on the data monitoring results and prediction results to perform fault detection and fault repair.

[0140] In one embodiment of the present invention, a component evaluation module 205 is further included, connected to the alarm module 204, and the component evaluation module 205 is used to perform:

[0141] Conduct life assessment on each component in the new energy power station, and classify each component into youth, middle-age and old age based on the usage time and the standard service life of the component, so as to set different inspection frequencies for components in different life stages, and remind operation and maintenance personnel to conduct inspections according to the corresponding inspection frequencies.

[0142] In one embodiment of the present invention, the alarm module 204 is used to perform:

[0143] When the value of a monitoring parameter or indicator exceeds the corresponding threshold range, an alarm message is sent to the operation and maintenance personnel, and the power zone information and component information related to the abnormal monitoring parameter or abnormal indicator are attached, so that the operation and maintenance personnel can perform fault troubleshooting and fault repair according to the order of the life cycle of the relevant components;

[0144] When the prediction result is abnormal, an early warning message is sent to the operation and maintenance personnel, and the location information and predicted status of the abnormal energy storage battery group are attached, so that the operation and maintenance personnel can prevent faults of the abnormal energy storage battery group.

[0145] In one embodiment of the present invention, the energy storage battery model in the prediction module 203 is created using the Modelica language.

[0146] In one embodiment of the present invention, the prediction module 203 is used to perform:

[0147] For each energy storage battery pack, execute:

[0148] Inputting the operating data of each single cell of the energy storage battery group into the corresponding energy storage battery group model to update the setting parameter values ​​of each single cell model in the energy storage battery group model accordingly;

[0149] The simulation scenario parameters are set according to the environmental data, so that the energy storage battery pack model runs under the current simulation scenario parameters, and the inconsistent capacity decay and thermal runaway of the energy storage battery pack are predicted.

[0150] In one embodiment of the present invention, it further includes an allocation module 206 for executing:

[0151] When at least one power zone fails to generate electricity, the required power generation of the faulty power zone is distributed to the remaining normal power zones based on the predicted failure coefficients and historical failure rates of the remaining normal power zones.

[0152] It should be noted that the intelligent analysis system for the operation data of the new energy power station provided in the above embodiment is only illustrated by the division of the above functional modules. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the system can be divided into different functional modules to complete all or part of the functions described above. In addition, the above system embodiment and the method embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0153] The embodiment of the present application also provides a computer device, please refer to Figure 3The computer device includes a processor and a memory, in which at least one instruction, at least one program, a code set or an instruction set is stored, and the at least one instruction, at least one program, a code set or an instruction set is loaded and executed by the processor to implement the intelligent analysis method of new energy power station operation data provided by the above-mentioned method embodiments.

[0154] An embodiment of the present application also provides a computer-readable storage medium, on which is stored at least one instruction, at least one program, code set or instruction set, and the at least one instruction, at least one program, code set or instruction set is loaded and executed by a processor to implement the intelligent analysis method of new energy power station operation data provided by the above-mentioned method embodiments.

[0155] An embodiment of the present application also provides a computer program product, which includes a computer program. A processor of a computer device reads the computer program from a computer-readable storage medium, and the processor executes the computer program, so that the computer device executes the intelligent analysis method for new energy power station operation data described in any of the above embodiments.

[0156] For the convenience of description, the above system or device is described as being divided into various modules or units according to their functions. Of course, when implementing the present application, the functions of each module can be implemented in the same or multiple software and / or hardware.

[0157] It can be known from the description of the above implementation methods that those skilled in the art can clearly understand that the present application can be implemented by means of software plus a necessary general hardware platform. Based on such an understanding, the technical solution of the present application can be essentially or partly contributed to the prior art in the form of a software product, which can be stored in a storage medium such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in the various embodiments of the present application or certain parts of the embodiments.

[0158] Finally, it should be noted that, in this article, relational terms such as first, second, third and fourth are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the statement "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0159] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for intelligent analysis of new energy power station operation data, characterized in that: include: Using various sensors to collect the operating data of the new energy power station in real time; wherein the operating data includes the power generation of each power zone in the new energy power station, the operating data of each single cell of the energy storage battery group and the environmental data; Based on the operation data, determine monitoring parameters and indicator values, and use the preset threshold ranges of each monitoring parameter and each indicator value to perform real-time data monitoring of each power area of ​​the new energy power station; Predicting the health status of each energy storage battery pack by using the operating data of each single battery of the energy storage battery pack, the environmental data and a pre-built energy storage battery pack model; Based on data monitoring and prediction results, alarm and early warning information are sent to operation and maintenance personnel to conduct fault detection and repair; The energy storage battery group model sets an optimization cycle. In each optimization time period, each energy storage battery group model is optimized in the following manner: Utilize the real-time operation data of each single battery in the energy storage battery pack at each moment in the current optimization time period and the energy storage battery pack model at the historical moment to predict the results at each moment in the current optimization time period, and optimize the target parameters in the battery system model; The method optimizes the target parameters in the battery system model by using the real-time operation data of each single battery in the energy storage battery pack at each moment in the current optimization time period and the energy storage battery pack model at the historical moment to predict the results at each moment in the current optimization time period, including: Based on the real-time operation data of each single battery in the energy storage battery group at each moment in the current optimization time period and the prediction results of the energy storage battery group model at the historical moment for the corresponding moment in the current optimization time period, the accuracy of the prediction results at each moment in the current optimization time period is scored; Determine the fitness function based on the accuracy score results at each moment in the current optimization time period; The target parameters to be optimized in the energy storage battery model are used to construct the positions and velocities of particles in the particle swarm-simulated annealing algorithm, and the initial annealing temperature and the final annealing temperature are determined; In each optimization cycle when the annealing temperature is less than the final annealing temperature, the following are performed: the speed and position of each particle in the particle group are updated, and the fitness function value of each particle after the update is calculated based on the fitness function, so as to determine whether the new position is acceptable based on the fitness function value of each particle after the update and the fitness function value of each particle before the update, and then the annealing temperature is updated; When the annealing temperature is greater than or equal to the final annealing temperature, the optimal solution is determined, and the optimization of the target parameters in the energy storage battery pack model is completed; The accuracy scoring method of the prediction results at each moment in the current optimization time period is: For each moment in the current optimization period, execute: Calculate the difference between the actual SOC change rate and the predicted SOC change rate of each single battery at the current moment, determine the number of single batteries whose difference is greater than a first preset threshold, and assign scores based on the number of single batteries whose difference is greater than the first preset threshold; Calculate the difference between the actual temperature and the predicted temperature of each single battery at the current moment, determine the number of single batteries whose difference is greater than the second preset threshold, and assign scores based on the number of single batteries whose difference is greater than the second preset threshold to obtain the accuracy score result at the current moment within the current optimization time period; After sending alarm and warning information to operation and maintenance personnel based on data monitoring results and prediction results to perform fault detection and fault repair, it also includes: When at least one power zone fails to generate electricity, the power generation capacity of the faulty power zone is distributed to the other normal power zones based on the predicted failure coefficients and historical failure rates of the other normal power zones. When at least one power area fails to generate electricity, based on the predicted failure coefficients and historical failure rates of the remaining normal power areas, the required power generation of the faulty power area is distributed to the remaining normal power areas, including: Sort the normal power areas in descending order based on the predicted fault coefficient of each normal power area; Allocate the required power generation capacity of the faulty power zone to each normal power zone in sequence. For each normal power zone, perform the following: B1, based on the current amount of electricity to be distributed divided by the number of normal power areas that are not currently distributed, determine the current amount of electricity to be distributed equally; B2, allocate the current normal power area based on the current equally shared power, the predicted failure coefficient of the current normal power area and the historical failure rate; B3, subtract the current allocation amount of the normal power zone from the amount of electricity to be allocated, to obtain a new amount of electricity to be allocated, so as to jump to step B1 to allocate electricity to the next normal power zone; Step B2 allocates the current normal power area in the following manner: ΔD=(1-bl)D Where ΔD is the current power distribution in the normal power area, b is the predicted fault coefficient, l is the historical fault rate, and D is the current equally divided power.

2. The method according to claim 1, characterized in that Also includes: Conduct life assessment on each component in the new energy power station, and classify each component into youth, middle-age and old age based on the usage time and the standard service life of the component, so as to set different inspection frequencies for components in different life stages, and remind operation and maintenance personnel to conduct inspections according to the corresponding inspection frequencies.

3. The method according to claim 2, characterized in that Based on the data monitoring results and prediction results, alarm and early warning information are sent to the operation and maintenance personnel to perform fault detection and fault repair, including: When the monitoring parameter or the indicator value exceeds the corresponding threshold range, an alarm message is sent to the operation and maintenance personnel, and the power zone information and component information related to the abnormal monitoring parameter or abnormal indicator are attached, so that the operation and maintenance personnel can perform fault troubleshooting and fault repair according to the order of the life cycle of the relevant components; When the prediction result is abnormal, an early warning message is sent to the operation and maintenance personnel, and the location information and predicted status of the abnormal energy storage battery group are attached, so that the operation and maintenance personnel can prevent faults of the abnormal energy storage battery group.

4. The method according to claim 1, characterized in that The energy storage battery pack model is created using the Modelica language.

5. The method according to claim 4, characterized in that The method uses the operating data and environmental data of each single cell of the energy storage battery pack and a pre-built energy storage battery pack model to predict the health status of each energy storage battery pack, including: For each energy storage battery pack, execute: Inputting the operating data of each single cell of the energy storage battery group into the corresponding energy storage battery group model to correspondingly update the setting parameter values ​​of each single cell model in the energy storage battery group model; The simulation scenario parameters are set according to the environmental data, so that the energy storage battery pack model is simulated and run under the current simulation scenario parameters, and the inconsistent capacity decay and thermal runaway of the energy storage battery pack are predicted.

6. A new energy power station operation data intelligent analysis system, used to implement the method described in any one of claims 1 to 5, characterized in that: The system comprises: A collection module is used to collect the operation data of the new energy power station in real time using various sensors; wherein the operation data includes the power generation of each power area in the new energy power station, the operation data of each single cell of the energy storage battery group, and the environmental data; A monitoring module, for determining monitoring parameters and index values ​​based on the operation data, and performing real-time data monitoring of each power area of ​​the new energy power station by using the preset threshold ranges of each monitoring parameter and each index value; A prediction module is used to predict the health status of each energy storage battery pack by using the operation data and environmental data of each single battery of the energy storage battery pack and a pre-built energy storage battery pack model; The alarm module is used to send alarm and early warning information to operation and maintenance personnel based on data monitoring results and prediction results to perform fault detection and repair.

7. A computer device, characterized in that: The computer device includes a memory and a processor, the memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory to implement the steps of any one of the methods described in claims 1-5.

8. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method described in any one of claims 1 to 5 are implemented.

9. A computer program product, characterized in that The method comprises a computer program, which, when executed by a processor, implements the steps of the method according to any one of claims 1 to 5.

Images