WO2025007286A1 - 一种电池回收利用的碳排放监测方法、系统、设备及介质 - Google Patents
一种电池回收利用的碳排放监测方法、系统、设备及介质 Download PDFInfo
- Publication number
- WO2025007286A1 WO2025007286A1 PCT/CN2023/105800 CN2023105800W WO2025007286A1 WO 2025007286 A1 WO2025007286 A1 WO 2025007286A1 CN 2023105800 W CN2023105800 W CN 2023105800W WO 2025007286 A1 WO2025007286 A1 WO 2025007286A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- recycling
- carbon emission
- scrap
- carbon
- battery
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Ceased
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/30—Administration of product recycling or disposal
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
Definitions
- the present invention relates to the technical field of carbon emission monitoring for battery recycling, and in particular to a carbon emission monitoring method, system, computer equipment and storage medium for battery recycling.
- the recycling of lithium batteries can not only protect the environment but also bring certain economic value to resource recycling.
- the existing recycling methods of waste lithium batteries mainly use pyrolysis and dry crushing and sorting to recover heavy metal elements in lithium batteries.
- the carbon emissions caused by the process or material loss in the recycling of lithium batteries will undoubtedly cause a certain degree of environmental pollution. Therefore, how to reasonably and effectively monitor the carbon emissions in the recycling process and control the carbon emissions in the classification and recycling of lithium batteries within a reasonable range has become a key issue for all relevant companies.
- the purpose of the present invention is to provide a carbon emission monitoring method for battery recycling, which is based on the scrap information of lithium batteries to classify scrapped batteries and determine the optimal recycling method, and obtain scientific and reasonable carbon emission monitoring targets according to the scrap classification and the optimal recycling method, and then combine effective evaluation indicators to reliably evaluate the carbon emissions of the lithium battery recycling process, so as to solve the application defects of the existing carbon emission monitoring methods for lithium battery recycling and provide a universal carbon emission monitoring method for lithium battery recycling. While developing a new measurement method, it can also achieve comprehensive and accurate integrated monitoring and scientific and reasonable evaluation of carbon emissions in the lithium battery recycling process, thereby providing reliable guarantees for the optimization of the lithium battery recycling process.
- an embodiment of the present invention provides a method for monitoring carbon emissions from battery recycling, the method comprising the following steps:
- a corresponding recycling value index is obtained, and based on the comparative analysis results of the actual total carbon emissions from recycling and the carbon emission monitoring target value, the carbon emissions of the recycling process of the lithium battery to be recycled are comprehensively evaluated in combination with the recycling value index to obtain a carbon emission evaluation result.
- the scrapping information includes an appearance image, a three-dimensional point cloud feature map and a battery capacity retention rate.
- the step of obtaining scrap information of lithium batteries to be recycled includes:
- the image data and point cloud data of the lithium battery to be recycled are collected by a laser scanning device, and the image data and point cloud data are preprocessed respectively to obtain a corresponding appearance image and a three-dimensional point cloud feature map;
- Rc 0 , -d and n represent the initial capacity retention rate, capacity attenuation coefficient and number of charging cycles respectively; Rc represents the battery capacity retention rate after n cycles.
- the scrap classification model includes a first classification module and a second classification module connected in sequence;
- the first classification module includes an ACmix network model;
- the step of inputting the scrap information into a pre-built scrap classification model for classification prediction to obtain the corresponding scrap type includes:
- scrapping types include appearance damage and deformation, liquid leakage, abnormal internal bulging and abnormal capacity retention rate;
- the step of determining the corresponding optimal recycling method according to the scrap type includes:
- the type recycling mapping relationship library is a database that stores the mapping relationship between the scrap type and the optimal recycling method.
- the carbon emission monitoring target value includes the total carbon emission target value of the recycling process and the corresponding carbon emission target values of each process step;
- the step of predicting the carbon emission of the recycled lithium battery according to the scrap type and the optimal recycling method to obtain the carbon emission monitoring target value comprises:
- the carbon emission target value of each process step is obtained.
- the step of comprehensively evaluating the carbon emissions of the recycling process of the lithium battery to be recycled based on the comparative analysis result of the actual total carbon emissions recycled and the carbon emission monitoring target value in combination with the recycling value index to obtain the carbon emission evaluation result includes:
- the carbon emission assessment result is set as qualified carbon emission; otherwise, the carbon emission assessment result is set as excessive carbon emission;
- the process steps to be optimized whose actual carbon emission exceeds the carbon emission target value of the corresponding process step in the carbon emission monitoring target value are obtained, and the carbon emission exceeding standard classification prompt is given to the process steps to be optimized.
- recovery value index is expressed as:
- I represents the recycling value index
- E inc and C rel represent the actual total economic income from recycling and the actual total carbon emissions from recycling, respectively.
- an embodiment of the present invention provides a carbon emission monitoring system for battery recycling, the system comprising:
- a type identification module is used to obtain the scrap information of the lithium battery to be recycled, and input the scrap information into a pre-built scrap classification model for classification prediction to obtain the corresponding scrap type;
- a target acquisition module is used to determine the corresponding optimal recycling method according to the scrap type, and to predict the recycling carbon emission of the lithium battery to be recycled according to the scrap type and the optimal recycling method to obtain a carbon emission monitoring target value;
- a carbon emission monitoring module used to recycle the lithium battery to be recycled according to the optimal recycling method, and obtain the actual total carbon emission and the actual total economic income of recycling according to the actual carbon emission and the actual recycling economic income corresponding to each process step;
- the carbon emission assessment module is used to obtain a corresponding recycling value index based on the actual total carbon emissions from recycling and the actual total economic income from recycling, and based on the comparative analysis results of the actual total carbon emissions from recycling and the carbon emission monitoring target value, combined with the recycling value index, comprehensively evaluate the carbon emissions of the recycling process of the lithium battery to be recycled to obtain a carbon emission assessment result.
- an embodiment of the present invention further provides a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above method when executing the computer program.
- an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the steps of the above method when executed by a processor.
- the present application provides a carbon emission monitoring method, system, computer equipment and storage medium for battery recycling.
- the method realizes that the scrap information of the obtained lithium battery to be recycled is input into the pre-built scrap classification model for classification prediction to obtain the scrap type, and the optimal recycling method is determined according to the scrap type.
- the recycling carbon emission of the lithium battery to be recycled is predicted to obtain the carbon emission monitoring target value
- the actual carbon emission and actual recycling economic income corresponding to each process step in the recycling process of the lithium battery to be recycled according to the optimal recycling method are obtained, and the actual total recycling carbon emission and actual total recycling economic income are obtained.
- the carbon emission of the recycling process of the lithium battery to be recycled is evaluated to obtain the technical solution of the carbon emission evaluation result.
- the carbon emission monitoring method for battery recycling can not only provide a universal carbon emission monitoring method for lithium battery recycling, but also realize comprehensive and accurate integrated monitoring and scientific and reasonable evaluation of carbon emissions in the lithium battery recycling process, thereby providing reliable guarantee for the optimization of lithium battery recycling process, and has high practical application value.
- FIG1 is a schematic diagram of an application scenario of a carbon emission monitoring method for battery recycling according to an embodiment of the present invention
- FIG2 is a schematic flow diagram of a method for monitoring carbon emissions from battery recycling in an embodiment of the present invention
- FIG3 is a schematic diagram of the structure of a scrap classification model according to an embodiment of the present invention.
- FIG4 is a schematic diagram of the structure of an ACmix network model in a scrap classification model according to an embodiment of the present invention.
- FIG5 is a schematic diagram of the structure of a carbon emission monitoring system for battery recycling according to an embodiment of the present invention.
- FIG. 6 is a diagram showing the internal structure of a computer device according to an embodiment of the present invention.
- the carbon emission monitoring method for battery recycling provided by the present invention can be applied to a terminal or server as shown in Figure 1.
- the terminal can be but is not limited to various personal computers, laptops, smart phones, tablet computers and portable wearable devices, and the server can be implemented with an independent server or a server cluster composed of multiple servers.
- the server can use the carbon emission monitoring method for battery recycling of the present invention to monitor and evaluate the carbon emissions of the recycling process of retired lithium batteries according to actual application requirements, and use the obtained carbon emission evaluation results for subsequent research on the server, or send them to the terminal for further analysis and research by the terminal user. It can not only provide a universal carbon emission monitoring method for lithium battery recycling, but also realize comprehensive and accurate integrated monitoring and evaluation of carbon emissions in the lithium battery recycling process. A scientific and reasonable evaluation can provide a reliable guarantee for the optimization of the lithium battery recycling process.
- the following embodiments will explain in detail the carbon emission monitoring method for battery recycling of the present invention.
- a method for monitoring carbon emissions from battery recycling comprising the following steps:
- scrap information can be understood as information that can directly or indirectly reflect the scrap status of lithium batteries to be recycled.
- this embodiment preferably collects information related to these three aspects of lithium batteries to be recycled to perform simple and effective scrap type identification; specifically, the scrap information includes an appearance image for detecting external damage or liquid leakage, a three-dimensional point cloud feature map for detecting internal bulging of the battery, and a battery capacity retention rate for detecting abnormal capacity retention rate; correspondingly, the step of obtaining scrap information of lithium batteries to be recycled includes:
- the image data and point cloud data of the lithium battery to be recycled are collected by a laser scanning device, and the image data and point cloud data are preprocessed respectively to obtain a corresponding appearance image and a three-dimensional point cloud feature map;
- the laser scanning device can be understood as a laser scanning device capable of acquiring the image data and point cloud data of the lithium battery to be recycled, and the specific type is not limited here;
- the corresponding image data preprocessing can be understood as an image preprocessing method selected according to the actual application requirements of the appearance image, including grayscale, geometric transformation and image enhancement (denoising) and other processing operations to eliminate irrelevant information and restore useful real information;
- the point cloud data preprocessing can be understood as a point cloud data preprocessing method selected according to the actual application requirements of the three-dimensional point cloud feature map, including denoising, simplification, registration, hole filling, normalization and depth map mapping and other processing operations to effectively remove noise and external points in the point cloud;
- the number of charge and discharge cycles of the lithium battery to be recycled is obtained, and the corresponding battery capacity retention rate is obtained according to the number of charge and discharge cycles and a preset battery capacity retention attenuation model; wherein the number of charge and discharge cycles can be understood as the number of charge and discharge cycles that the lithium battery to be recycled has experienced during normal operation; the battery capacity retention rate can be understood as the difference between the actual battery capacity and the battery capacity retention rate.
- Rc 0 , -d and n represent the initial capacity retention rate, capacity attenuation coefficient and number of charging cycles respectively; Rc represents the battery capacity retention rate after n cycles;
- the above-mentioned scrap classification model for identifying the scrap type of recycled lithium batteries can be understood as being obtained by obtaining a large number of appearance images, three-dimensional point cloud feature maps and battery capacity retention rates of retired lithium batteries, and performing corresponding type annotations to obtain a scrap information data set for training; specifically, as shown in FIG3 , the scrap classification model includes a first classification module and a second classification module connected in sequence; wherein, in principle, the first classification module can adopt a network model with image and point cloud data recognition functions, but considering the accuracy and efficiency of the initial classification, this embodiment preferably adopts the ACmix network model shown in FIG4 that integrates the self-attention mechanism and the convolution operation in the deep neural network, which first uses the convolution operation to input The input features are mapped to obtain rich intermediate features, and then the convolution operation and self-attention mechanism are used to reuse and aggregate the intermediate features, which combines the advantages of both convolution operation and self-attention mechanism, avoids complex secondary projection operations, and effectively improves the efficiency and accuracy of image classification and recognition applications; the ACmix
- the step of inputting the scrap information into a pre-built scrap classification model for classification prediction to obtain the corresponding scrap type includes:
- the appearance image and the three-dimensional point cloud feature map are input into the first classification module for classification and recognition to obtain the corresponding initial classification result; wherein the initial classification result can be understood as a fusion feature map extracted based on self-attention and convolution through the ACmix network model
- the classification results obtained by identifying the scrapped types of recycled lithium batteries include four categories: external damage, liquid leakage, internal bulging of the battery, and normal.
- the specific acquisition process is as follows:
- the input appearance image and 3D point cloud feature map are projected through 3 1 ⁇ 1 convolutions, and then the deformation function (reshape) is operated into N fragments. Therefore, a rich set of intermediate features containing 3 ⁇ N feature maps is obtained;
- a fully connected layer MLP Multilayer Perceptron
- MLP Multilayer Perceptron
- the intermediate features obtained above are grouped into N groups, each group contains 3 features, and each feature comes from a 1 ⁇ 1 convolution; the corresponding three feature maps are used as query, key and value respectively, and the traditional multi-head self-attention module is used for operation and calculation;
- the feature tensors generated by the two paths are weightedly added to generate a fused feature map with a dimension of H ⁇ W ⁇ C.
- the fused feature map is then input into a preset classifier for classification to obtain the corresponding initial classification result.
- the scrap type acquisition process can be understood as, when the initial classification result obtained is abnormal, that is, the aforementioned external damage and deformation, liquid leakage or internal bulging of the battery, the initial classification result is directly used as the obtained scrap type; when the initial classification result obtained is normal, that is, it is not identified as any type of external damage, liquid leakage or internal bulging of the battery, it is necessary to perform capacity retention rate abnormality detection on it, and obtain the final scrap type according to the abnormality detection result; it should be noted that the capacity retention rate abnormality detection can be understood as judging the battery capacity retention rate corresponding to the lithium battery to be recycled based on the capacity retention rate threshold obtained by the aforementioned statistical analysis. If the battery capacity retention rate has decayed to the preset capacity retention rate threshold, it is considered that the
- scrap type determine the corresponding optimal recycling method, and according to the scrap type and the optimal recycling method, predict the recycled carbon emissions of the lithium battery to be recycled to obtain the carbon emission monitoring target value; wherein the scrap type is the scrap category of the lithium battery determined by the above method steps, including appearance damage and deformation, liquid leakage, internal abnormal bulging and abnormal capacity retention rate; it should be noted that in actual application, the specific categories of scrap classification can be increased or decreased according to actual conditions and needs;
- dry recycling mainly refers to a method for directly realizing the recovery of various battery materials or valuable metals without using a solution or other medium, mainly including mechanical sorting and high-temperature decomposition; the crude product obtained by dry recycling can be further subjected to high-temperature thermal repair to obtain positive and negative electrode materials containing certain impurities, or the organic binder in the electrode material can be removed by pyrometallurgy, and the metal and its compounds therein can undergo oxidation-reduction reactions and condense and recover, and the metal in the slag can be recovered by screening, pyrolysis, magnetic separation or chemical methods; wet recycling uses various acidic and alkaline solutions as transfer media to transfer metal ions from the electrode material to the leachate, and then extracts the metal ions from the solution in the form of salts, oxides, etc.
- ion exchange precipitation, adsorption, etc.
- biological recovery mainly uses microbial leaching to convert the useful components of the system into soluble compounds and selectively dissolve them, so as to separate the target components from the impurity components and recover valuable metals such as lithium, cobalt and nickel;
- the above-mentioned optimal recycling method refers to the most suitable recycling method selected from the above-mentioned three recycling methods according to the scrap type; specifically, the step of determining the corresponding optimal recycling method according to the scrap type includes:
- a pre-built type recycling mapping relationship library is searched to obtain the corresponding optimal recycling method; wherein the type recycling mapping relationship library can be understood as a database established based on the research results of selecting different recycling methods for a large number of scrapped lithium batteries of various scrap types collected, for example, dry recycling is used for external damage or abnormal capacity retention rate, and wet recycling is used for liquid leakage or internal bulging of the battery.
- the above-mentioned scrap The recycling method corresponding to the type is only an exemplary description and can be selected based on existing research results or actual application needs. No specific limitation is made here.
- the above-mentioned carbon emission monitoring target value can be understood as the target upper limit value of the carbon emission during the recycling process of the battery to be recycled, including the total target value of carbon emission during the recycling process and the corresponding carbon emission target value of each process step; specifically, the step of predicting the carbon emission of the recycling of the lithium battery to be recycled according to the scrap type and the optimal recycling method to obtain the carbon emission monitoring target value includes:
- the battery model, capacity, weight, scrap type and optimal recycling method are input into a pre-built carbon emission regression prediction model for combined prediction to obtain the total target value of carbon emissions in the recycling process;
- the carbon emission regression prediction model can be understood as a multivariate linear regression model established in advance based on the battery model, capacity, weight, scrap type, recycling method and corresponding carbon emission values of a large number of scrapped batteries, with the carbon emission value as the dependent variable and other variables as independent variables.
- the specific mathematical model representation can be determined based on the data collected in actual applications, and is not limited here;
- the carbon emission target value of each process step is obtained; wherein, the carbon emission target value of each process step can be understood as the total carbon emission target value of the recycling process multiplied by the historical carbon emission proportion of the corresponding process step.
- the total carbon emission target value of the recycling process is A
- the historical carbon emission proportion of the first process step in the corresponding optimal recycling method is w%
- the corresponding carbon emission target value of each process step is A*w%
- the historical carbon emission proportion of the process step can also be obtained by collecting a large amount of relevant historical data for analysis, which will not be described in detail here.
- the actual carbon emissions include direct carbon emissions and indirect carbon emissions; for example, when the optimal recycling method is determined to be dry recycling, the corresponding direct carbon emissions can be understood as the carbon emissions directly generated by the recycling process
- the amount of carbon dioxide gas can be obtained by installing corresponding carbon dioxide gas monitoring devices and monitoring the gas flow and carbon dioxide concentration generated during the recovery process through infrared technology; indirect carbon emissions can be understood as the carbon emissions generated by the use of energy (such as electricity, natural gas, gasoline and steam, etc.), material use (liquid nitrogen, water, acid and alkali reagents, extractants, precipitants, etc.) and depreciation of production equipment during the recovery process, which can be expressed as:
- C ind represents indirect carbon emissions
- E i and ⁇ en,i represent the i-th energy usage and the corresponding carbon emission coefficient respectively
- M j and ⁇ ma,j represent the j-th material usage and the corresponding carbon emission coefficient respectively
- D k and ⁇ de,k represent the k-th equipment depreciation value and the corresponding carbon emission coefficient respectively;
- the actual recycling economic income can be understood as the economic income that can be obtained by directly selling the materials obtained in each process step, which can be reasonably calculated according to the actual recycling process steps, and is not specifically limited here; for example, the recycling economic value generated by obtaining valuable metals such as copper, aluminum, lithium, cobalt, manganese, nickel and their compounds, graphite, diaphragm, and positive and negative electrode materials;
- the actual total recycling carbon emissions and actual total recycling economic income of the entire recycling process can be obtained by adding them up, which will not be described in detail here.
- a corresponding recycling value index is obtained, and based on the comparative analysis results of the actual total carbon emissions from recycling and the carbon emission monitoring target value, the recycling process carbon emissions of the lithium battery to be recycled are comprehensively evaluated in combination with the recycling value index to obtain a carbon emission evaluation result; wherein, in principle, the carbon emission evaluation result can be directly evaluated by judging whether the carbon emissions in the actual recycling process exceed the corresponding target value, but in actual applications, the fact that carbon emissions do not exceed the standard can only prove that the carbon emissions in the recycling process are up to standard, and does not necessarily guarantee that the recycling can achieve the expected economic value.
- this embodiment preferably combines the carbon emission monitoring target value, the actual total carbon emissions from recycling and the actual economic income from recycling to establish a scientific and reasonable evaluation index, and judges whether the actual total carbon emissions from recycling are small or large.
- the above recycling value index can be understood as an indicator for judging whether the recycling income obtained has actual economic significance relative to the recycling carbon emissions. Specifically, the recycling value index is expressed as:
- I represents the recycling value index
- E inc and C rel represent the actual total economic income from recycling and the actual total carbon emissions from recycling, respectively;
- the step of comprehensively evaluating the carbon emissions of the recycling process of the lithium battery to be recycled based on the comparative analysis result of the actual total carbon emissions recycled and the carbon emission monitoring target value in combination with the recycling value index to obtain the carbon emission evaluation result includes:
- the carbon emission assessment result is set as qualified carbon emission; otherwise, the carbon emission assessment result is set as excessive carbon emission;
- the process of obtaining the above carbon emission assessment results can be understood as follows: when the actual total carbon emission from recycling is less than the total target value of carbon emission from the recycling process, it is necessary to further determine that the obtained recycling value index is greater than the preset value threshold value, in order to obtain the carbon emission assessment result that the carbon emission does not exceed the standard (the carbon emission is qualified); on the contrary, if the actual total carbon emission from recycling is greater than the total target value of carbon emission from the recycling process, or the actual total carbon emission from recycling is less than the total target value of carbon emission from the recycling process, and the recycling value index is less than the preset value threshold value, the obtained carbon emission assessment result is that the carbon emission exceeds the standard, which proves that there is room for carbon emission optimization in the recycling method, and the process steps to be optimized can be further determined according to the actual carbon emissions collected in each process step and the actual recycling economic income for relevant optimization guidance;
- the process steps to be optimized whose actual carbon emission exceeds the carbon emission target value of the corresponding process step in the carbon emission monitoring target value are obtained, and the process steps to be optimized are graded and prompted for carbon emission exceeding the standard;
- the process steps to be optimized can be understood as the process steps with carbon emission exceeding the standard obtained by screening according to the actual carbon emission of each process step, and the actual carbon emission corresponding to each process step can be directly compared and analyzed with the corresponding process step carbon emission target value, and the process steps whose actual carbon emission exceeds the process step carbon emission target value can be found as the process steps to be optimized, and the specific values of the calculated actual carbon emission exceeding the process step carbon emission target value are ranked in descending order, and graded and prompted for carbon emission exceeding the standard according to the ranking, for example, the process steps ranked higher are given a higher prompt level, that is, there is more room for optimization, and optimization solutions are urgently needed; the process steps ranked lower are given a relatively low
- the corresponding process recovery value index can be further calculated based on the actual carbon emissions and the actual recycling economic income, and the obtained process recovery value index and the specific value of the actual carbon emissions exceeding the carbon emission target value of the process steps are weighted and summed according to the preset weight value, and then the summed results are ranked in descending order, and graded prompts for carbon emissions exceeding the standard are given according to the ranking, for example, process steps with higher rankings are given higher prompt levels, and process steps with lower rankings are given relatively lower prompt levels; it should be noted that the aforementioned preset weight values can be selected and determined according to actual application needs, and are not limited here.
- the scrap information of the obtained lithium battery to be recycled is input into a pre-built scrap classification model for classification prediction to obtain the scrap type, and the optimal recycling method is determined according to the scrap type.
- the optimal recycling method is determined according to the scrap type.
- the technical solution is to classify lithium batteries and determine the optimal recycling method based on their scrap information, and obtain scientific and reasonable carbon emission monitoring targets based on the scrap classification and the optimal recycling method. Combined with effective evaluation indicators, the carbon emissions in the lithium battery recycling process are reliably evaluated, which effectively solves the application defects of the existing carbon emission monitoring methods for lithium battery recycling. It can not only provide a universal carbon emission monitoring method for lithium battery recycling, but also realize comprehensive and accurate integrated monitoring and scientific and reasonable evaluation of carbon emissions in the lithium battery recycling process, thereby providing reliable guarantee for the optimization of the lithium battery recycling process, and has high practical application value.
- a carbon emission monitoring system for battery recycling comprising:
- the type identification module 1 is used to obtain the scrap information of the lithium battery to be recycled, and input the scrap information into a pre-built scrap classification model for classification prediction to obtain the corresponding scrap type;
- Target acquisition module 2 used to determine the corresponding optimal recycling method according to the scrap type, and predict the recycled carbon emissions of the lithium battery to be recycled according to the scrap type and the optimal recycling method, to obtain the carbon emission monitoring target value;
- the carbon emission monitoring module 3 is used to recycle the lithium battery to be recycled according to the optimal recycling method, and obtain the actual total carbon emission and the actual total economic income of recycling according to the actual carbon emission and the actual recycling economic income corresponding to each process step;
- the carbon emission assessment module 4 is used to obtain a corresponding recycling value index based on the actual total carbon emissions from recycling and the actual total economic income from recycling, and based on the comparative analysis results of the actual total carbon emissions from recycling and the carbon emission monitoring target value, combined with the recycling value index, comprehensively evaluate the carbon emissions of the recycling process of the lithium battery to be recycled to obtain a carbon emission assessment result.
- each module in the above-mentioned carbon emission monitoring system for battery recycling can be implemented in whole or in part through software, hardware and their combination.
- the above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.
- FIG6 shows an internal structure diagram of a computer device in an embodiment, and the computer device can specifically be a terminal or a server.
- the computer device includes a processor, a memory, a network interface, a display, a camera, and an input device connected via a system bus.
- the processor of the computer device is used to provide computing and control capabilities.
- the memory of the computer device includes a non-volatile storage medium and an internal memory.
- the non-volatile storage medium stores an operating system and a computer program.
- the internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium.
- the network interface of the computer device is used to communicate with an external terminal through a network connection.
- the display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen
- the input device of the computer device can be a touch layer covered on the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.
- FIG. 6 is merely a block diagram of a portion of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied.
- a specific computing device may include more or fewer components than those shown in the figure, or combine certain components, or have the same component arrangement.
- a computer device including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the steps of the above method are implemented when the processor executes the computer program.
- a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the steps of the above method are implemented.
- an embodiment of the present invention provides a carbon emission monitoring method and system for battery recycling.
- the carbon emission monitoring method for battery recycling realizes inputting the scrap information of the acquired lithium battery to be recycled into a pre-built scrap classification model for classification prediction to obtain the scrap type, and determining the optimal recycling method according to the scrap type, and predicting the recycling carbon emissions of the lithium battery to be recycled to obtain the carbon emission monitoring target value, and then based on the actual carbon emissions and actual recycling economic income corresponding to each process step in the recycling treatment of the lithium battery to be recycled according to the optimal recycling method, the actual total recycling carbon emissions and the actual total recycling economic income are obtained, and combined with the carbon emission monitoring target value, the carbon emissions of the recycling process of the lithium battery to be recycled are evaluated, and a technical solution for obtaining the carbon emission evaluation results is obtained.
- This method can not only provide a universal carbon emission monitoring method for lithium battery recycling, but also realize comprehensive and accurate integrated monitoring and scientific and reasonable evaluation of carbon emissions in the lithium battery recycling process, thereby providing reliable guarantee for the optimization of the lithium battery recycling process, and
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Sustainable Development (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Databases & Information Systems (AREA)
- Computing Systems (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Secondary Cells (AREA)
- Processing Of Solid Wastes (AREA)
Abstract
本发明提供了一种电池回收利用的碳排放监测方法、系统、设备及介质，所述方法为将获取的待回收锂电池的报废信息输入预先构建的报废分类模型进行分类预测得到报废类型，并根据报废类型确定最优回收方法，对待回收锂电池进行回收碳排量预测得到碳排放监测目标值后，并根据获取的待回收锂电池按照最优回收方法进行回收处理中各个工艺步骤对应的实际碳排量和实际回收经济收入，得到的实际回收总碳排量和实际回收总经济收入，结合碳排放监测目标值，对待回收锂电池的回收过程碳排放进行评估，得到碳排放评估结果。本发明不仅能为锂电池回收提供普适性碳排放监测方法，而且能实现对锂电池回收过程的碳排放进行全面精准的一体化监测和科学合理的评估。
Description
本发明涉及电池回收碳排放监测技术领域，特别是涉及一种电池回收利用的碳排放监测方法、系统、计算机设备及存储介质。
锂电池回收利用既可以保护环境也可以使得资源回收利用带来一定的经济价值，且现有废旧锂电池回收利用方法主要是对锂电池采用热解法和干法破碎分选以回收锂电池里面的重金属元素等。然而，锂电池回收利用过程中工艺或物料耗损必然会造成的碳排放，无疑给出环境造成一定程度的污染，那么，如何对回收过程中的碳排量进行合理有效的监测，使得锂电池分类回收中碳排放控制在合理范围内成为各个相关企业重点关注的问题。
现有锂电池回收利用的碳排放监测大都侧重于对热解法和干法破碎分选等回收方法的碳排放核算，并未关注基于电池报废类型的碳排放监测研究和碳排放监测目标的合理制定，且碳排放合理性监测评价过程并未考虑经济收入与碳排放的均衡性，并不能真正实现对锂电池回收利用过程中碳排放的科学合理监测，以及真正有效的评价闭环管理一体化。
发明内容
本发明的目的是提供一种电池回收利用的碳排放监测方法，基于锂电池报废信息进行报废分类和最优回收方法确定，并根据报废分类和最优回收方法得到科学合理的碳排监测目标，再结合有效的评价指标对锂电池回收过程的碳排放进行可靠评估，解决现有锂电池回收利用的碳排放监测方法的应用缺陷，为锂电池回收提供普适性碳排放监
测方法的同时，还能实现对锂电池回收过程碳排放进行全面精准的一体化监测和科学合理的评估，进而为锂电池回收工艺流程优化提供可靠保障。
为了实现上述目的，有必要针对上述技术问题，提供了一种电池回收利用的碳排放监测方法及系统。
第一方面，本发明实施例提供了一种电池回收利用的碳排放监测方法，所述方法包括以下步骤：
获取待回收锂电池的报废信息，并将所述报废信息输入预先构建的报废分类模型进行分类预测，得到对应的报废类型；
根据所述报废类型，确定对应的最优回收方法，并根据所述报废类型和所述最优回收方法，对所述待回收锂电池进行回收碳排量预测，得到碳排放监测目标值；
将所述待回收锂电池按照所述最优回收方法进行回收处理，并根据获取的各个工艺步骤对应的实际碳排量和实际回收经济收入，得到实际回收总碳排量和实际回收总经济收入；
根据所述实际回收总碳排量和所述实际回收总经济收入，得到对应的回收价值指数，并基于所述实际回收总碳排量与所述碳排放监测目标值的对比分析结果，结合所述回收价值指数对所述待回收锂电池的回收过程碳排放进行综合评估，得到碳排放评估结果。
进一步地，所述报废信息包括外观图像、三维点云特征图和电池容量保持率。
进一步地，所述获取待回收锂电池的报废信息的步骤包括：
通过激光扫描装置采集所述待回收锂电池的影像数据和点云数据，并分别对所述影像数据和点云数据进行预处理，得到对应的外观图像和三维点云特征图；
获取所述待回收锂电池的充放电循环次数，并根据所述充放电循环次数和预设的电池容量保持衰减模型，得到对应的电池容量保持率；所述电池容量保持率表示为：
Rc＝Rc0e-dn
Rc＝Rc0e-dn
其中，Rc0、-d和n分别表示初始容量保持率、容量衰减系数和充电循环次数；Rc表示循环n次后的电池容量保持率。
进一步地，所述报废分类模型包括依次连接的第一分类模块和第二分类模块；所述第一分类模块包括ACmix网络模型；
所述将所述报废信息输入预先构建的报废分类模型进行分类预测，得到对应的报废类型的步骤包括：
将所述外观图像和所述三维点云特征图输入所述第一分类模块进行分类识别，得到对应的初始分类结果；
判断所述初始分类结果是否正常，若否，则将所述初始分类结果作为对应的报废类型；若是，则将对应的电池容量保持率输入所述第二分类模块进行异常检查，并根据对应的异常检查结果，得到对应的报废类型。
进一步地，所述报废类型包括外观破损变形、液体泄漏、内部异常鼓包和容量保持率异常；
所述根据所述报废类型，确定对应的最优回收方法的步骤包括：
根据所述报废类型，查找预先构建的类型回收映射关系库，得到对应的最优回收方法；所述类型回收映射关系库为存储报废类型与最优回收方法之间映射关系的数据库。
进一步地，所述碳排放监测目标值包括回收过程碳排放总目标值和对应的各个工艺步骤碳排放目标值；
所述根据所述报废类型和所述最优回收方法，对所述待回收锂电池回收利用的碳排量进行预测，得到碳排放监测目标值的步骤包括：
获取所述待回收锂电池的电池型号、容量和重量；
将所述电池型号、容量、重量、报废类型和最优回收方法输入至预先构建的碳排放回归预测模型进行组合预测，得到所述回收过程碳排放总目标值；
根据所述回收过程碳排放总目标值和所述最优回收方法中各个工艺步骤的历史碳排占比，得到各个工艺步骤碳排放目标值。
进一步地，所述基于所述实际回收总碳排量与所述碳排放监测目标值的对比分析结果，结合所述回收价值指数对所述待回收锂电池的回收过程碳排放进行综合评估，得到碳排放评估结果的步骤包括：
判断所述实际回收总碳排量是否小于所述碳排放监测目标值中的回收过程碳排放总目标值，若否，则将所述碳排放评估结果设为碳排超标，反之，则判断所述回收价值指数是否大于预设价值阈值；
若所述回收价值指数大于所述预设价值阈值，则将所述碳排放评估结果设为碳排合格，反之，则将所述碳排放评估结果设为碳排超标；
当所述碳排放评估结果为碳排超标时，获取实际碳排量超过所述碳排放监测目标值中对应工艺步骤碳排放目标值的待优化工艺步骤，并对所述待优化工艺步骤进行碳排放超标分级提示。
进一步地，所述回收价值指数表示为：
其中，I表示回收价值指数；Einc和Crel分别表示实际回收总经济收入和实际回收总碳排量。
第二方面，本发明实施例提供了一种电池回收利用的碳排放监测系统，所述系统包括：
类型识别模块，用于获取待回收锂电池的报废信息，并将所述报废信息输入预先构建的报废分类模型进行分类预测，得到对应的报废类型；
目标获取模块，用于根据所述报废类型，确定对应的最优回收方法，并根据所述报废类型和所述最优回收方法，对所述待回收锂电池进行回收碳排量预测，得到碳排放监测目标值；
碳排监测模块，用于将所述待回收锂电池按照所述最优回收方法进行回收处理，并根据获取的各个工艺步骤对应的实际碳排量和实际回收经济收入，得到实际回收总碳排量和实际回收总经济收入；
碳排评估模块，用于根据所述实际回收总碳排量和所述实际回收总经济收入，得到对应的回收价值指数，并基于所述实际回收总碳排量与所述碳排放监测目标值的对比分析结果，结合所述回收价值指数对所述待回收锂电池的回收过程碳排放进行综合评估，得到碳排放评估结果。
第三方面，本发明实施例还提供了一种计算机设备，包括存储器、处理器及存储在存储器上并可在处理器上运行的计算机程序，所述处理器执行所述计算机程序时实现上述方法的步骤。
第四方面，本发明实施例还提供一种计算机可读存储介质，其上存储有计算机程序，所述计算机程序被处理器执行时实现上述方法的步骤。
上述本申请提供了一种电池回收利用的碳排放监测方法、系统、计算机设备和存储介质，通过所述方法实现了将获取的待回收锂电池的报废信息输入预先构建的报废分类模型进行分类预测得到报废类型，并根据报废类型确定最优回收方法，对待回收锂电池进行回收碳排量预测得到碳排放监测目标值后，并根据获取的待回收锂电池按照最优回收方法进行回收处理中各个工艺步骤对应的实际碳排量和实际回收经济收入，得到的实际回收总碳排量和实际回收总经济收入，结合碳排放监测目标值，对待回收锂电池的回收过程碳排放进行评估，得到碳排放评估结果的技术方案。与现有技术相比，该电池回收利用的碳排放监测方法，不仅能为锂电池回收提供普适性碳排放监测方法，而且能实现对锂电池回收过程碳排放进行全面精准的一体化监测和科学合理的评估，进而为锂电池回收工艺流程优化提供可靠保障，具有较高的实际应用价值。
图1是本发明实施例中电池回收利用的碳排放监测方法的应用场景示意图；
图2是本发明实施例中电池回收利用的碳排放监测方法的流程示意图；
图3是本发明实施例中报废分类模型的结构示意图；
图4是本发明实施例的报废分类模型中ACmix网络模型的结构示意图；
图5是本发明实施例中电池回收利用的碳排放监测系统的结构示意图；
图6是本发明实施例中计算机设备的内部结构图。
为了使本申请的目的、技术方案和有益效果更加清楚明白，下面结合附图及实施例，对本发明作进一步详细说明，显然，以下所描述的实施例是本发明实施例的一部分，仅用于说明本发明，但不用来限制本发明的范围。基于本发明中的实施例，本领域普通技术人员在没有作出创造性劳动前提下所获得的所有其他实施例，都属于本发明保护的范围。
本发明提供的电池回收利用的碳排放监测方法，可以应用于如图1所示的终端或服务器上。其中，终端可以但不限于是各种个人计算机、笔记本电脑、智能手机、平板电脑和便携式可穿戴设备，服务器可以用独立的服务器或者是多个服务器组成的服务器集群来实现。服务器可根据实际应用需求，采用本发明的电池回收利用的碳排放监测方法对退役锂电池回收利用过程的碳排放量进行监测和评估，并将得到的碳排放评估结果用于服务器后续的研究，或发送至终端供终端使用者进一步分析研究使用，不仅能为锂电池回收提供普适性碳排放监测方法，还能实现对锂电池回收过程碳排放进行全面精准的一体化监测和
科学合理的评估，进而为锂电池回收工艺流程优化提供可靠保障；下述实施例将对本发明的电池回收利用的碳排放监测方法进行详细说明。
在一个实施例中，如图2所示，提供了一种电池回收利用的碳排放监测方法，包括以下步骤：
S11、获取待回收锂电池的报废信息，并将所述报废信息输入预先构建的报废分类模型进行分类预测，得到对应的报废类型；其中，报废信息可理解为是能够直接或间接体现待回收锂电池报废情况的信息，基于现有报废锂电池通常存在外观异常(外部破损或液体泄漏)、内部结构异常(电池内部鼓包)或容量保持率异常三种可能性，本实施例优选地，对采集待回收锂电池这三方面相关的信息，以进行简单有效的报废类型识别；具体的，所述报废信息包括用于对外部破损或液体泄漏进行检测的外观图像、用于对电池内部鼓包进行检测的三维点云特征图和用于对容量保持率异常进行检测的电池容量保持率；对应的，所述获取待回收锂电池的报废信息的步骤包括：
通过激光扫描装置采集所述待回收锂电池的影像数据和点云数据，并分别对所述影像数据和点云数据进行预处理，得到对应的外观图像和三维点云特征图；其中，激光扫描装置可理解为能够获取待回收锂电池的影像数据和点云数据的激光扫描设备，具体类型此处不作限制；对应的影像数据的预处理可理解为是根据外观图像的实际应用需求而选用的图像预处理方式，包括灰度化、几何变换和图像增强(去噪)等消除无关信息和恢复有用真实信息的处理操作；同样的，点云数据的预处理可理解为是根据三维点云特征图的实际应用需求而选用的点云数据预处理方式，包括去噪声、简化、配准、补洞、归一化和深度图映射等有效剔除点云中的噪声和外点的处理操作；
获取所述待回收锂电池的充放电循环次数，并根据所述充放电循环次数和预设的电池容量保持衰减模型，得到对应的电池容量保持率；其中，充放电循环次数可理解为是待回收锂电池正常运行过程中已经经历的充放电循环次数；电池容量保持率可理解为是电池实际容量与
额定容量的比值，在使用期间，电池剩余容量伴随充放电次数增加而减少，且容量保持率随充放电循环次数的衰退规律符合幂函数关系，经过采集大量退役锂电池的循环充电次数与容量保持率数据，拟合的对应的电池容量保持衰减模型，表示为：
Rc＝Rc0e-dn
Rc＝Rc0e-dn
其中，Rc0、-d和n分别表示初始容量保持率、容量衰减系数和充电循环次数；Rc表示循环n次后的电池容量保持率；
上述用于对待回收锂电池进行报废类型识别的报废分类模型可理解为是根据获取大量退役锂电池的外观图像、三维点云特征图和电池容量保持率，并进行相应的类型标注得到报废信息数据集训练得到；具体的，如图3所示，所述报废分类模型包括依次连接的第一分类模块和第二分类模块；其中，第一分类模块原则上可以采用具有图像和点云数据识别功能的网络模型即可，但考虑的初始分类的精准性和高效性，本实施例优选的采用图4所示的将深度神经网络中的自注意力机制和卷积操作进行融合的ACmix网络模型，其通过先使用卷积操作对输入特征进行映射处理得到丰富的中间特征，再分别以卷积操作和自注意力机制重用及聚合中间特征的处理方式，融合了卷积操作和自注意力机制两者的优点，避免复杂的二次投影操作的同时，有效提升图像分类识别应用的效率和精准性；该ACmix网络模型可理解为是采用大量退役锂电池的外观图像和三维点云特征图进行标注训练得到参数稳定的ACmix网络结构的图像分类识别模型；第二分类模块可理解为是基于大量退役锂电池的电池容量保持率进行统计分析得到的容量保持率阈值，对待回收锂电池的容量保持率进行异常检查的处理模块；
具体的，所述将所述报废信息输入预先构建的报废分类模型进行分类预测，得到对应的报废类型的步骤包括：
将所述外观图像和所述三维点云特征图输入所述第一分类模块进行分类识别，得到对应的初始分类结果；其中，初始分类结果可理解为是通过ACmix网络模型进行基于自注意力和卷积提取的融合特征图
对待回收锂电池进行报废类型识别得到的分类结果，包括外部破损、液体泄漏、电池内部鼓包和正常等4类，具体获取过程如下：
在第一阶段：通过3个1×1卷积对输入的外观图像和三维点云特征图进行投影，然后变形函数(reshape)操作为N个片段。因此，获得了包含3×N特征映射的一组丰富的中间特征；
在第二阶段：收到中间特征后，采用全连接层MLP(Multilayer Perceptron)，生成非线性特征映射；然后通过对生成的特征进行转移和聚合，形成对输入特征进行卷积处理，这样可以像传统的CNN网络一样从局部感受野抽取有用的特征信息；
对于自注意力路径，将上述所得的中间特征集合到N组中，每组包含3个特征，每个特征来自1×1卷积；对应的三个特征图分别作为query、key和value，利用传统的多头自注意力模块进行操作计算；
最后，将两个路径生成的特征张量进行加权相加，生成了维数为H×W×C的融合特征图后，将该融合特征图输入预设分类器进行分类处理，得到对应的初始分类结果。
判断所述初始分类结果是否正常，若否，则将所述初始分类结果作为对应的报废类型，反之，则将对应的电池容量保持率输入所述第二分类模块进行异常检查，并根据对应的异常检查结果，得到对应的报废类型；其中，报废类型的获取过程可理解为是，当得到的初始分类结果为不正常，即前述的外部破损变形、液体泄漏或电池内部鼓包时，则直接将初始分类结果作为得到的报废类型；当得到的初始分类结果为正常，即没有被识别为外部破损、液体泄漏或电池内部鼓包任一类型时，则需要对其进行容量保持率异常检测，并根据异常检测结果得到最终的报废类型；需要说明的是，容量保持率异常检测可理解为是基于前述统计分析得到的容量保持率阈值对待回收锂电池对应的电池容量保持率进行判断，若电池容量保持率已衰减至预设的容量保持率阈值，则认为给锂电池的容量保持率异常。
S12、根据所述报废类型，确定对应的最优回收方法，并根据所述报废类型和所述最优回收方法，对所述待回收锂电池进行回收碳排量预测，得到碳排放监测目标值；其中，报废类型为通过上述方法步骤确定的锂电池报废类别，包括外观破损变形、液体泄漏、内部异常鼓包和容量保持率异常；需要说明的是，在实际应用中，可根据实际情况和需求增加或减少报废分类的具体类别；
现有的锂电池回收方法主要分为干法回收、湿法回收和生物回收，其中，干法回收主要是指不通过溶液等媒介，直接实现各类电池材料或有价金属的回收方法，主要包括机械分选和高温分解；通过干法回收得到的粗产品可再通过高温热修复，得到含有一定杂质的正、负极材料，或通过火法冶金去除电极材料中的有机粘结剂，且使其中的金属及其化合物发生氧化还原反应并冷凝回收，以及对炉渣中的金属采用筛分、热解、磁选或化学方法回收；湿法回收是以各种酸碱性溶液为转移媒介，将金属离子从电极材料中转移到浸出液中，再通过离子交换、沉淀、吸附等手段将金属离子以盐、氧化物等形式从溶液中提取出来，主要包括湿法冶金、化学萃取以及离子交换等方法；生物回收主要是利用微生物浸出，将体系的有用组分转化为可溶化合物并选择性地溶解出来，实现目标组分与杂质组分分离，回收锂、钴和镍等有价金属；
上述最优回收方法指根据报废类型从上述三种回收方法中选取的最适合的回收方式；具体地，所述根据所述报废类型，确定对应的最优回收方法的步骤包括：
根据所述报废类型，查找预先构建的类型回收映射关系库，得到对应的最优回收方法；其中，类型回收映射关系库可理解为是基于采集的各种报废类型的大量报废锂电池选用不同回收方法的研究结果分析建立的数据库，比如，外部破损或容量保持率异常采用干法回收、液体泄漏或电池内部鼓包采用湿法回收等；需要说明的是，上述报废
类型对应的回收方法仅为示例性描述，可基于现有研究成果或实际应用需求进行选取，此处不作具体限定。
上述碳排放监测目标值可理解为是预测得到的待回收电池回收过程中碳排放量的目标上限值，包括回收过程碳排放总目标值和对应的各个工艺步骤碳排放目标值；具体的，所述根据所述报废类型和所述最优回收方法，对所述待回收锂电池回收利用的碳排量进行预测，得到碳排放监测目标值的步骤包括：
获取所述待回收锂电池的电池型号、容量和重量；
将所述电池型号、容量、重量、报废类型和最优回收方法输入至预先构建的碳排放回归预测模型进行组合预测，得到所述回收过程碳排放总目标值；其中，碳排放回归预测模型可理解为是预先根据大量报废电池的电池型号、容量、重量、报废类型、回收方法和对应的碳排放值，以碳排放值为因变量，其他变量为自变量建立的多元线性回归模型，具体的数学模型表示可根据实际应用中采集的数据拟合确定，此处不作限制；
根据所述回收过程碳排放总目标值和所述最优回收方法中各个工艺步骤的历史碳排占比，得到各个工艺步骤碳排放目标值；其中，各个工艺步骤碳排放目标值可理解为采用回收过程碳排放总目标值乘以对应的工艺步骤的历史碳排占比值得到，比如，回收过程碳排放总目标值为A，对应最优回收方法中第一个工艺步骤的历史碳排占比为w％，则对应的该各个工艺步骤碳排放目标值为A*w％；对应的，工艺步骤的历史碳排占比同样可通过采集大量相关历史数据分析得到，此处不再详述。
S13、将所述待回收锂电池按照所述最优回收方法进行回收处理，并根据获取的各个工艺步骤对应的实际碳排量和实际回收经济收入，得到实际回收总碳排量和实际回收总经济收入；其中，实际碳排量包括直接碳排量和间接碳排量；比如，确定的最优回收方法干法回收中的拆解回收时，对应的，直接碳排量可理解为是回收过程直接产生的
二氧化碳气体量，可通过安装相应的二氧化碳气体监测装置，通过红外技术监测回收过程中产生的气体流量和二氧化碳浓度的方式得到；间接碳排量可理解为是回收过程中能源使用(如，电能、天然气、汽油和蒸汽等)、物料使用(液氮、水、酸碱试剂、萃取剂、沉淀剂等)和生产设备折旧等经过换算产生的碳排放量，可表示为：
其中，Cind表示间接碳排量；Ei和λen,i分别表示第i种能源使用量及对应的碳排系数；Mj和λma,j分别表示第j种物料使用量及对应的碳排系数；Dk和λde,k分别表示第k种设备折旧值及对应的碳排系数；
同时，实际回收经济收入可理解为是各个工艺步骤得到材料直接售出可获取的经济收入，可根据实际回收工艺步骤的情况进行合理计算，此处不作具体限定；比如，得到铜、铝、锂、钴、锰、镍等有价金属及其化合物，石墨、隔膜、以及正、负极材料等产生的回收经济价值；
通过上述方法得到各个工艺步骤的实际碳排量和实际回收经济收入后，将其累加就可得到整个回收过程的实际回收总碳排量和实际回收总经济收入，此处不再详述。
S14、根据所述实际回收总碳排量和所述实际回收总经济收入，得到对应的回收价值指数，并基于所述实际回收总碳排量与所述碳排放监测目标值的对比分析结果，结合所述回收价值指数对所述待回收锂电池的回收过程碳排放进行综合评估，得到碳排放评估结果；其中，碳排放评估结果原则上可直接通过判断实际回收过程中碳排放是否超过对应目标值的方式评估得到，但在实际应用中，碳排放未超标仅可证明回收过程的碳排放量是达标的，并不一定能保证回收能达到预期的经济价值，为了保证回收评估更贴合实际应用，本实施例优选地将碳排放监测目标值、实际回收总碳排量和实际回收经济收入结合使用建立科学合理的评价指标的方式，通过判断实际回收总碳排量是否小
于碳排放监测目标值，以及回收经济收入相对碳排放是否有意义所得到的碳排放监测结果，以及在整个过程碳排放超标时，可以优化的碳排放超标工艺步骤的最终评估结果；
上述回收价值指数可理解为是判断得到的回收收入相对于回收碳排放而言是否有实际经济意义的指标，具体的，所述回收价值指数表示为：
其中，I表示回收价值指数；Einc和Crel分别表示实际回收总经济收入和实际回收总碳排量；
具体的，所述基于所述实际回收总碳排量与所述碳排放监测目标值的对比分析结果，结合所述回收价值指数对所述待回收锂电池的回收过程碳排放进行综合评估，得到碳排放评估结果的步骤包括：
判断所述实际回收总碳排量是否小于所述碳排放监测目标值中的回收过程碳排放总目标值，若否，则将所述碳排放评估结果设为碳排超标，反之，则判断所述回收价值指数是否大于预设价值阈值；其中，预设价值阈值可根据实际情况选取，此处不作具体限制；
若所述回收价值指数大于所述预设价值阈值，则将所述碳排放评估结果设为碳排合格，反之，则将所述碳排放评估结果设为碳排超标；
上述碳排放评估结果的获取过程可理解为：当实际回收总碳排量小于回收过程碳排放总目标值时，需要进一步判断得到的回收价值指数大于预设价值阈值时，才能得到碳排放评估结果为碳排未超标(碳排合格)，反之，若实际回收总碳排量大于回收过程碳排放总目标值，或者，实际回收总碳排量小于回收过程碳排放总目标值，且回收价值指数小于预设价值阈值时，得到的碳排放评估结果为碳排超标，就证明该回收方法存在碳排放优化空间，可根据各个工艺步骤采集的实际碳排量和实际回收经济收入进一步确定待优化工艺步骤进行相关的优化指导；
当所述碳排放评估结果为碳排超标时，获取实际碳排量超过所述碳排放监测目标值中的对应工艺步骤碳排放目标值的待优化工艺步骤，并对所述待优化工艺步骤进行碳排放超标分级提示；其中，待优化工艺步骤的可理解为是根据各个工艺步骤的实际碳排量筛选得到的碳排超标的工艺步骤，可直接将各个工艺步骤对应的实际碳排量与对应的工艺步骤碳排放目标值进行对比分析，找出实际碳排量超过工艺步骤碳排放目标值的工艺步骤作为待优化工艺步骤，并根据计算得到的实际碳排量超过工艺步骤碳排放目标值的具体数值进行降序排名，并根据排序名次进行碳排放超标分级提示，比如排名靠前的工艺步骤，给出提示级别更高，即优化空间更大，亟需优化解决；排名靠后的工艺步骤，给出的提示级别相对较低，即优化空间不太大，可以根据实际情况选择是否需要优化；
同时，为了保证待优化工艺步骤和对应分级提示的合理性，还可以在找出实际碳排量超过工艺步骤碳排放目标值的工艺步骤后，进一步根据实际碳排量和实际回收经济收入计算对应的工艺回收价值指数，并将得到的工艺回收价值指数和实际碳排量超过工艺步骤碳排放目标值的具体数值按照预设权重值进行加权求和，再将求和得到的结果进行降序排名，并根据排序名次进行碳排放超标分级提示，比如排名靠前的工艺步骤，给出提示级别更高，排名靠后的工艺步骤，给出的提示级别相对较低；需要说明的是，前述预设权重值可根据实际应用需求选取确定，此处不作限定。
本申请实施例通过将获取的待回收锂电池的报废信息输入预先构建的报废分类模型进行分类预测得到报废类型，并根据报废类型确定最优回收方法，对待回收锂电池进行回收碳排量预测得到碳排放监测目标值后，并根据获取的待回收锂电池按照最优回收方法进行回收处理中各个工艺步骤对应的实际碳排量和实际回收经济收入，得到的实际回收总碳排量和实际回收总经济收入，结合碳排放监测目标值，对待回收锂电池的回收过程碳排放进行评估，得到碳排放评估结果的技
术方案，通过基于锂电池报废信息进行报废分类和最优回收方法确定，并根据报废分类和最优回收方法得到科学合理的碳排监测目标，再结合有效的评价指标对锂电池回收过程的碳排放进行可靠评估，有效解决了现有锂电池回收利用的碳排放监测方法的应用缺陷，不仅能为锂电池回收提供普适性碳排放监测方法，而且能实现对锂电池回收过程碳排放进行全面精准的一体化监测和科学合理的评估，进而为锂电池回收工艺流程优化提供可靠保障，具有较高的实际应用价值。
需要说明的是，虽然上述流程图中的各个步骤按照箭头的指示依次显示，但是这些步骤并不是必然按照箭头指示的顺序依次执行。除非本文中有明确的说明，这些步骤的执行并没有严格的顺序限制，这些步骤可以以其它的顺序执行。
在一个实施例中，如图5所示，提供了一种电池回收利用的碳排放监测系统，所述系统包括：
类型识别模块1，用于获取待回收锂电池的报废信息，并将所述报废信息输入预先构建的报废分类模型进行分类预测，得到对应的报废类型；
目标获取模块2，用于根据所述报废类型，确定对应的最优回收方法，并根据所述报废类型和所述最优回收方法，对所述待回收锂电池进行回收碳排量预测，得到碳排放监测目标值；
碳排监测模块3，用于将所述待回收锂电池按照所述最优回收方法进行回收处理，并根据获取的各个工艺步骤对应的实际碳排量和实际回收经济收入，得到实际回收总碳排量和实际回收总经济收入；
碳排评估模块4，用于根据所述实际回收总碳排量和所述实际回收总经济收入，得到对应的回收价值指数，并基于所述实际回收总碳排量与所述碳排放监测目标值的对比分析结果，结合所述回收价值指数对所述待回收锂电池的回收过程碳排放进行综合评估，得到碳排放评估结果。
关于电池回收利用的碳排放监测系统的具体限定可以参见上文中
对于电池回收利用的碳排放监测方法的限定，对应的技术效果也可等同得到，在此不再赘述。上述电池回收利用的碳排放监测系统中的各个模块可全部或部分通过软件、硬件及其组合来实现。上述各模块可以硬件形式内嵌于或独立于计算机设备中的处理器中，也可以以软件形式存储于计算机设备中的存储器中，以便于处理器调用执行以上各个模块对应的操作。
图6示出一个实施例中计算机设备的内部结构图，该计算机设备具体可以是终端或服务器。如图6所示，该计算机设备包括通过系统总线连接的处理器、存储器、网络接口、显示器、摄像头和输入装置。其中，该计算机设备的处理器用于提供计算和控制能力。该计算机设备的存储器包括非易失性存储介质、内存储器。该非易失性存储介质存储有操作系统和计算机程序。该内存储器为非易失性存储介质中的操作系统和计算机程序的运行提供环境。该计算机设备的网络接口用于与外部的终端通过网络连接通信。该计算机程序被处理器执行时以实现电池回收利用的碳排放监测方法。该计算机设备的显示屏可以是液晶显示屏或者电子墨水显示屏，该计算机设备的输入装置可以是显示屏上覆盖的触摸层，也可以是计算机设备外壳上设置的按键、轨迹球或触控板，还可以是外接的键盘、触控板或鼠标等。
本领域普通技术人员可以理解，图6中示出的结构，仅仅是与本申请方案相关的部分结构的框图，并不构成对本申请方案所应用于其上的计算机设备的限定，具体的计算设备可以包括比图中所示更多或更少的部件，或者组合某些部件，或者具有同的部件布置。
在一个实施例中，提供了一种计算机设备，包括存储器、处理器及存储在存储器上并可在处理器上运行的计算机程序，处理器执行计算机程序时实现上述方法的步骤。
在一个实施例中，提供了一种计算机可读存储介质，其上存储有计算机程序，计算机程序被处理器执行时实现上述方法的步骤。
综上，本发明实施例提供的一种电池回收利用的碳排放监测方法及系统，其电池回收利用的碳排放监测方法实现了将获取的待回收锂电池的报废信息输入预先构建的报废分类模型进行分类预测得到报废类型，并根据报废类型确定最优回收方法，对待回收锂电池进行回收碳排量预测得到碳排放监测目标值后，并根据获取的待回收锂电池按照最优回收方法进行回收处理中各个工艺步骤对应的实际碳排量和实际回收经济收入，得到的实际回收总碳排量和实际回收总经济收入，结合碳排放监测目标值，对待回收锂电池的回收过程碳排放进行评估，得到碳排放评估结果的技术方案，该方法不仅能为锂电池回收提供普适性碳排放监测方法，而且能实现对锂电池回收过程碳排放进行全面精准的一体化监测和科学合理的评估，进而为锂电池回收工艺流程优化提供可靠保障，具有较高的实际应用价值。
本说明书中的各个实施例均采用递进的方式描述，各个实施例直接相同或相似的部分互相参见即可，每个实施例重点说明的都是与其他实施例的不同之处。尤其，对于系统实施例而言，由于其基本相似于方法实施例，所以描述的比较简单，相关之处参见方法实施例的部分说明即可。需要说明的是，上述实施例的各技术特征可以进行任意的组合，为使描述简洁，未对上述实施例中的各个技术特征所有可能的组合都进行描述，然而，只要这些技术特征的组合不存在矛盾，都应当认为是本说明书记载的范围。
以上所述实施例仅表达了本申请的几种优选实施方式，其描述较为具体和详细，但并不能因此而理解为对发明专利范围的限制。应当指出的是，对于本技术领域的普通技术人员来说，在不脱离本发明技术原理的前提下，还可以做出若干改进和替换，这些改进和替换也应视为本申请的保护范围。因此，本申请专利的保护范围应以所述权利要求的保护范围为准。
Claims (11)
- 一种电池回收利用的碳排放监测方法，其特征在于，所述方法包括以下步骤：获取待回收锂电池的报废信息，并将所述报废信息输入预先构建的报废分类模型进行分类预测，得到对应的报废类型；根据所述报废类型，确定对应的最优回收方法，并根据所述报废类型和所述最优回收方法，对所述待回收锂电池进行回收碳排量预测，得到碳排放监测目标值；将所述待回收锂电池按照所述最优回收方法进行回收处理，并根据获取的各个工艺步骤对应的实际碳排量和实际回收经济收入，得到实际回收总碳排量和实际回收总经济收入；根据所述实际回收总碳排量和所述实际回收总经济收入，得到对应的回收价值指数，并基于所述实际回收总碳排量与所述碳排放监测目标值的对比分析结果，结合所述回收价值指数对所述待回收锂电池的回收过程碳排放进行综合评估，得到碳排放评估结果。
- 如权利要求1所述的电池回收利用的碳排放监测方法，其特征在于，所述报废信息包括外观图像、三维点云特征图和电池容量保持率。
- 如权利要求2所述的电池回收利用的碳排放监测方法，其特征在于，所述获取待回收锂电池的报废信息的步骤包括：通过激光扫描装置采集所述待回收锂电池的影像数据和点云数据，并分别对所述影像数据和点云数据进行预处理，得到对应的外观图像和三维点云特征图；获取所述待回收锂电池的充放电循环次数，并根据所述充放电循环次数和预设的电池容量保持衰减模型，得到对应的电池容量保持率；所述电池容量保持率表示为：
Rc＝Rc0e-dn其中，Rc0、-d和n分别表示初始容量保持率、容量衰减系数和充电循环次数；Rc表示循环n次后的电池容量保持率。 - 如权利要求2所述的电池回收利用的碳排放监测方法，其特征在于，所述报废分类模型包括依次连接的第一分类模块和第二分类模块；所述第一分类模块包括ACmix网络模型；所述将所述报废信息输入预先构建的报废分类模型进行分类预测，得到对应的报废类型的步骤包括：将所述外观图像和所述三维点云特征图输入所述第一分类模块进行分类识别，得到对应的初始分类结果；判断所述初始分类结果是否正常，若否，则将所述初始分类结果作为对应的报废类型；若是，则将对应的电池容量保持率输入所述第二分类模块进行异常检查，并根据对应的异常检查结果，得到对应的报废类型。
- 如权利要求1所述的电池回收利用的碳排放监测方法，其特征在于，所述报废类型包括外观破损变形、液体泄漏、内部异常鼓包和容量保持率异常；所述根据所述报废类型，确定对应的最优回收方法的步骤包括：根据所述报废类型，查找预先构建的类型回收映射关系库，得到对应的最优回收方法；所述类型回收映射关系库为存储报废类型与最优回收方法之间映射关系的数据库。
- 如权利要求1所述的电池回收利用的碳排放监测方法，其特征在于，所述碳排放监测目标值包括回收过程碳排放总目标值和对应的各个工艺步骤碳排放目标值；所述根据所述报废类型和所述最优回收方法，对所述待回收锂电池回收利用的碳排量进行预测，得到碳排放监测目标值的步骤包括：获取所述待回收锂电池的电池型号、容量和重量；将所述电池型号、容量、重量、报废类型和最优回收方法输入至预先构建的碳排放回归预测模型进行组合预测，得到所述回收过程碳排放总目标值；根据所述回收过程碳排放总目标值和所述最优回收方法中各个工艺步骤的历史碳排占比，得到各个工艺步骤碳排放目标值。
- 如权利要求6所述的电池回收利用的碳排放监测方法，其特征在于，所述基于所述实际回收总碳排量与所述碳排放监测目标值的对比分析结果，结合所述回收价值指数对所述待回收锂电池的回收过程碳排放进行综合评估，得到碳排放评估结果的步骤包括：判断所述实际回收总碳排量是否小于所述碳排放监测目标值中的回收过程碳排放总目标值，若否，则将所述碳排放评估结果设为碳排超标，反之，则判断所述回收价值指数是否大于预设价值阈值；若所述回收价值指数大于所述预设价值阈值，则将所述碳排放评估结果设为碳排合格，反之，则将所述碳排放评估结果设为碳排超标；当所述碳排放评估结果为碳排超标时，获取实际碳排量超过所述碳排放监测目标值中对应工艺步骤碳排放目标值的待优化工艺步骤，并对所述待优化工艺步骤进行碳排放超标分级提示。
- 如权利要求1所述的电池回收利用的碳排放监测方法，其特征在于，所述回收价值指数表示为：
其中，I表示回收价值指数；Einc和Crel分别表示实际回收总经济收入和实际回收总碳排量。 - 一种电池回收利用的碳排放监测系统，其特征在于，所述系统包括：类型识别模块，用于获取待回收锂电池的报废信息，并将所述报废信息输入预先构建的报废分类模型进行分类预测，得到对应的报废类型；目标获取模块，用于根据所述报废类型，确定对应的最优回收方法，并根据所述报废类型和所述最优回收方法，对所述待回收锂电池进行回收碳排量预测，得到碳排放监测目标值；碳排监测模块，用于将所述待回收锂电池按照所述最优回收方法进行回收处理，并根据获取的各个工艺步骤对应的实际碳排量和实际回收经济收入，得到实际回收总碳排量和实际回收总经济收入；碳排评估模块，用于根据所述实际回收总碳排量和所述实际回收总经济收入，得到对应的回收价值指数，并基于所述实际回收总碳排量与所述碳排放监测目标值的对比分析结果，结合所述回收价值指数对所述待回收锂电池的回收过程碳排放进行综合评估，得到碳排放评估结果。
- 一种计算机设备，包括存储器、处理器及存储在存储器上并可在处理器上运行的计算机程序，其特征在于，所述处理器执行所述计算机程序时实现权利要求1至8中任一所述方法的步骤。
- 一种计算机可读存储介质，其上存储有计算机程序，其特征在于，所述计算机程序被处理器执行时实现权利要求1至8中任一所述方法的步骤。
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| PCT/CN2023/105800 WO2025007286A1 (zh) | 2023-07-05 | 2023-07-05 | 一种电池回收利用的碳排放监测方法、系统、设备及介质 |
| CN202380009735.8A CN117099115A (zh) | 2023-07-05 | 2023-07-05 | 一种电池回收利用的碳排放监测方法、系统、设备及介质 |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| PCT/CN2023/105800 WO2025007286A1 (zh) | 2023-07-05 | 2023-07-05 | 一种电池回收利用的碳排放监测方法、系统、设备及介质 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2025007286A1 true WO2025007286A1 (zh) | 2025-01-09 |
Family
ID=88772025
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2023/105800 Ceased WO2025007286A1 (zh) | 2023-07-05 | 2023-07-05 | 一种电池回收利用的碳排放监测方法、系统、设备及介质 |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN117099115A (zh) |
| WO (1) | WO2025007286A1 (zh) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119761924A (zh) * | 2025-03-06 | 2025-04-04 | 中铁七局集团广州工程有限公司 | 一种基于大数据分析的企业碳排放智能监测与管理方法 |
| CN121189652A (zh) * | 2025-11-24 | 2025-12-23 | 中交天津港湾工程设计院有限公司 | 基于沉管管节质量的碳排放量预测方法 |
| CN121190280A (zh) * | 2025-03-17 | 2025-12-23 | 中国环境科学研究院 | 碳排放数据的检测方法及检测平台 |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119313318A (zh) * | 2024-12-17 | 2025-01-14 | 广东省锐驰新能源科技有限公司 | 基于多端分析的废旧锂电池回收管理系统、方法及介质 |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20210216932A1 (en) * | 2018-06-26 | 2021-07-15 | Ihi Corporation | Non-transitory computer-readable recording medium storing energy system optimization program, energy system optimization method, and energy system optimization device |
| CN113673987A (zh) * | 2020-05-14 | 2021-11-19 | 上海电盛科技有限公司 | 基于区块链的退役电池管理方法及设备 |
| CN114897226A (zh) * | 2022-04-25 | 2022-08-12 | 广东邦普循环科技有限公司 | 一种碳排放量预测方法、装置、设备及存储介质 |
| CN116029743A (zh) * | 2022-10-28 | 2023-04-28 | 国网辽宁省电力有限公司经济技术研究院 | 一种适用于零碳园区的碳足迹溯源方法及装置 |
| CN116362710A (zh) * | 2022-12-21 | 2023-06-30 | 上海第二工业大学 | 一种退役动力锂电池回收再利用全流程碳减排效益的计算方法 |
-
2023
- 2023-07-05 CN CN202380009735.8A patent/CN117099115A/zh active Pending
- 2023-07-05 WO PCT/CN2023/105800 patent/WO2025007286A1/zh not_active Ceased
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20210216932A1 (en) * | 2018-06-26 | 2021-07-15 | Ihi Corporation | Non-transitory computer-readable recording medium storing energy system optimization program, energy system optimization method, and energy system optimization device |
| CN113673987A (zh) * | 2020-05-14 | 2021-11-19 | 上海电盛科技有限公司 | 基于区块链的退役电池管理方法及设备 |
| CN114897226A (zh) * | 2022-04-25 | 2022-08-12 | 广东邦普循环科技有限公司 | 一种碳排放量预测方法、装置、设备及存储介质 |
| CN116029743A (zh) * | 2022-10-28 | 2023-04-28 | 国网辽宁省电力有限公司经济技术研究院 | 一种适用于零碳园区的碳足迹溯源方法及装置 |
| CN116362710A (zh) * | 2022-12-21 | 2023-06-30 | 上海第二工业大学 | 一种退役动力锂电池回收再利用全流程碳减排效益的计算方法 |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119761924A (zh) * | 2025-03-06 | 2025-04-04 | 中铁七局集团广州工程有限公司 | 一种基于大数据分析的企业碳排放智能监测与管理方法 |
| CN119761924B (zh) * | 2025-03-06 | 2025-06-06 | 中铁七局集团广州工程有限公司 | 一种基于大数据分析的企业碳排放智能监测与管理方法 |
| CN121190280A (zh) * | 2025-03-17 | 2025-12-23 | 中国环境科学研究院 | 碳排放数据的检测方法及检测平台 |
| CN121189652A (zh) * | 2025-11-24 | 2025-12-23 | 中交天津港湾工程设计院有限公司 | 基于沉管管节质量的碳排放量预测方法 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117099115A (zh) | 2023-11-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113158947B (zh) | 一种动力电池健康评分方法、系统及存储介质 | |
| CN117099115A (zh) | 一种电池回收利用的碳排放监测方法、系统、设备及介质 | |
| Dui et al. | IoT-enabled fault prediction and maintenance for smart charging piles | |
| CN110824270A (zh) | 结合台区线损和异常事件的窃电用户辨识方法及装置 | |
| CN107145966A (zh) | 基于逻辑回归概率分析优化模型的反窃电分析预警方法 | |
| CN119598102B (zh) | 一种用于数据要素处理操作的合规评估的数据处理方法 | |
| Reza et al. | Gravitational search algorithm based LSTM deep neural network for battery capacity and remaining useful life prediction with uncertainty | |
| CN119204664B (zh) | 基于李群流形与时序知识图谱的交通事故预测方法及系统 | |
| CN118777883B (zh) | 车辆电池故障诊断方法、装置、设备及存储介质 | |
| Pandit et al. | A standardized comparative framework for machine learning techniques in lithium-ion battery state of health Estimation | |
| CN118884232A (zh) | 电池健康状态评估方法、装置、设备及存储介质 | |
| Lin et al. | Retired battery screening based on rebooted auxiliary classifier generative adversarial network and improved gramian angular field | |
| Acaro Chacón et al. | RecyBat24: a dataset for detecting lithium-ion batteries in electronic waste disposal | |
| Nguyen et al. | Electricity theft detection in power grid with a hybrid convolutional neural network-support vector machine model | |
| CN120125225A (zh) | 一种配电变压器精细化回收决策方法及系统 | |
| Isnaeni et al. | Comparison of k-nearest neighbors (knn) and decision tree with binary particle swarm optimization (bpso) in predicting employee performance | |
| CN119904330A (zh) | 基于图神经网络的智能电价匹配与核查方法及相关装置 | |
| Zhu et al. | Electricity Bill Recovery Risk Prediction Based on Machine Learning Algorithm | |
| CN110175200A (zh) | 一种基于人工智能算法的异常用能分析方法及系统 | |
| Jiangnan et al. | RETRACTED: Intelligent monitoring and economic benefits of electric vehicle thermal energy cycle based on artificial intelligence algorithms | |
| CN116451955A (zh) | 一种居民小区电动汽车充放电行为监控方法及系统 | |
| CN115878801A (zh) | 一种事件处理方法、装置、电子设备及存储介质 | |
| Ahmed et al. | Exploration of an E-waste Prediction Model for Collection System Optimization Using Deep Learning Models in E-waste Management Facilities | |
| Han et al. | Artificial Intelligence Based Risk Prediction System for Electricity Bill Recovery | |
| Andriani et al. | Integration of Artificial Intelligence into Battery Energy Storage System Fault Diagnosis: A Review |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 23944020 Country of ref document: EP Kind code of ref document: A1 |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |