Carbon emission calculation method considering energy characteristics of semiconductor industry chain

Abstract

The invention discloses a carbon emission calculation method considering energy characteristics of a semiconductor industry chain. The method comprises the following steps: acquiring a plurality of current energy consumption data of a current semiconductor production chain in a production process; performing data feature extraction on the current energy consumption data to obtain current data features of the current energy consumption data; and determining the current carbon emission of the current semiconductor production chain in the production process based on the current data characteristics and the historical carbon emission. According to the technical scheme, the carbon emission in the production process of the semiconductor production chain can be accurately calculated, a producer can be restrained to make a production plan based on the carbon emission, energy conservation and emission reduction are achieved, and diversification, high efficiency, quality and cleanliness of energy supply in an industrial gathering area are achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of industrial production carbon emission accounting, and in particular to a method for calculating carbon emissions taking into account the energy characteristics of the semiconductor industry chain. Background Art

[0002] The increasingly serious greenhouse effect has aroused people's increasing attention to the issue of greenhouse gas emissions. Reducing global carbon emissions has become an urgent and important issue to maintain the global living environment. Energy is an important material basis for economic and social development, and it is also the main source of carbon emissions.

[0003] In the industrial field, the energy demand types of production processes in the industrial chain of various industries are diverse, and the energy quality and reliability requirements are high, which puts forward higher requirements for the rational planning and operation of the integrated energy system. Taking the semiconductor industry as an example, the semiconductor industry includes different process flows such as silicon raw material preparation, wafer processing and chip manufacturing and testing. The energy demand in the production cluster of the same link is basically the same, and the energy quality, energy type and energy use cycle of different production groups in different links are not the same. The existing industrial integrated energy system often focuses on the energy demand of independent industrial links and does not consider carbon emissions. Summary of the invention

[0004] The present invention provides a method for calculating carbon emissions by taking into account the energy characteristics of the semiconductor industry chain, thereby achieving accurate calculation of carbon emissions on the semiconductor production chain.

[0005] In a first aspect, the embodiments of the present disclosure provide a method for calculating carbon emissions taking into account the energy characteristics of the semiconductor industry chain, including:

[0006] Obtain multiple current energy consumption data of the current semiconductor production chain during the production process;

[0007] Extracting data features from each of the current energy usage data to obtain current data features of the current energy usage data;

[0008] Based on the current data characteristics and historical carbon emissions, the current carbon emissions of the current semiconductor production chain during the production process are determined.

[0009] In a second aspect, the present disclosure provides a carbon emission calculation device that takes into account the energy characteristics of the semiconductor industry chain, including:

[0010] A data acquisition module is used to acquire multiple current energy consumption data of the current semiconductor production chain during the production process;

[0011] A feature extraction module, used to extract data features from each of the current energy consumption data to obtain current data features of the current energy consumption data;

[0012] The carbon emission calculation module is used to determine the current carbon emissions of the current semiconductor production chain during the production process based on the current data characteristics and historical carbon emissions.

[0013] In a third aspect, an embodiment of the present disclosure provides an electronic device, including:

[0014] at least one processor; and

[0015] a memory communicatively connected to at least one processor; wherein,

[0016] The memory stores a computer program that can be executed by at least one processor, and the computer program is executed by at least one processor so that the at least one processor can execute a carbon emissions calculation method that takes into account the energy characteristics of the semiconductor industry chain provided in the first aspect embodiment above.

[0017] In a fourth aspect, an embodiment of the present disclosure provides a computer-readable storage medium, which stores computer instructions, and the computer instructions are used to enable a processor to implement a carbon emissions calculation method that takes into account the energy characteristics of the semiconductor industry chain provided in the embodiment of the first aspect above when executing.

[0018] In a fifth aspect, an embodiment of the present disclosure provides a computer program product, which includes a computer program. When the computer program is executed by a processor, it implements a carbon emissions calculation method that takes into account the energy characteristics of the semiconductor industry chain provided in the embodiment of the first aspect above.

[0019] A carbon emission calculation method that takes into account the energy characteristics of the semiconductor industry chain in an embodiment of the present invention is implemented by obtaining multiple current energy consumption data of the current semiconductor production chain during the production process; extracting data features of each current energy consumption data to obtain the current data features of the current energy consumption data; and determining the current carbon emissions of the current semiconductor production chain during the production process based on the current data features and historical carbon emissions. The above technical solution can accurately calculate the carbon emissions of the production process on the semiconductor production chain, which helps to constrain producers to formulate production plans based on carbon emissions, achieve energy conservation and emission reduction, and realize the diversification, efficiency, quality and cleanliness of energy supply in industrial agglomeration areas.

[0020] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

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

[0022] Figure 1 It is a flow chart of a method for calculating carbon emissions taking into account energy characteristics of the semiconductor industry chain provided in the first embodiment of the present invention;

[0023] Figure 2 This is an example display diagram of current energy consumption data in the semiconductor industry chain provided by the first embodiment of the present invention;

[0024] Figure 3 This is a flow chart of a method for calculating carbon emissions taking into account energy characteristics of the semiconductor industry chain provided in Embodiment 2 of the present invention;

[0025] Figure 4 This is an example display diagram of the current carbon emissions in the semiconductor industry chain provided by the second embodiment of the present invention;

[0026] Figure 5 This is a schematic diagram of the structure of a carbon emission calculation device taking into account the energy characteristics of the semiconductor industry chain provided in the third embodiment of the present invention;

[0027] Figure 6 It is a structural schematic diagram of an electronic device provided in Embodiment 4 of the present invention. DETAILED DESCRIPTION

[0028] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme 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 only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0029] It should be noted that the terms "first", "second" and "target" in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0030] Embodiment 1

[0031] Figure 1 It is a flow chart of a method for calculating carbon emissions taking into account the energy characteristics of the semiconductor industry chain provided in Example 1 of the present invention. This embodiment can be applied to situations where carbon emissions are calculated based on current energy consumption data of each manufacturing process in the semiconductor production process. The method can be executed by a carbon emissions calculation device taking into account the energy characteristics of the semiconductor industry chain. The carbon emissions calculation device taking into account the energy characteristics of the semiconductor industry chain can be implemented in the form of hardware and / or software.

[0032] like Figure 1 As shown, the method includes:

[0033] S101. Obtain multiple current energy consumption data of the current semiconductor production chain during the production process.

[0034] In this embodiment, the semiconductor manufacturing process in the semiconductor production chain is divided into eight steps: wafer processing, oxidation, photolithography, etching, thin film deposition, interconnection, testing and packaging. Different links in different steps require different electrical, thermal and cold requirements. Among them, wafer processing and oxidation are the processes of manufacturing and obtaining wafers and forming a layer of oxide film on their surface. The process links have high requirements for ambient temperature and need to be carried out in a high temperature environment of 800 to 1200 degrees Celsius. Therefore, the demand for thermal energy is high, and electric energy is used as an auxiliary. Photolithography and etching are the processes of "printing" the circuit diagram on the wafer. Most of the current processes use wet etching methods, which have high requirements for cold energy and electric energy as an auxiliary. Thin film deposition and interconnection are to separate and connect different components such as transistors or storage units on the wafer to realize the transmission and reception of power and signals, and have high requirements for power quality. Testing and packaging are the processes of checking whether the semiconductor chip meets the standard and forming a protective shell on the chip that meets the standard to realize the exchange of electrical signals with the outside world, and have high requirements for power quality. The production link in the semiconductor industry chain is a multi-energy link coupling, combining thermal energy, cold energy and electric energy to realize semiconductor manufacturing.

[0035] In this embodiment, the current energy consumption data at least includes wafer processing energy consumption data, oxidation energy consumption data, lithography energy consumption data, etching energy consumption data, thin film deposition energy consumption data, interconnection energy consumption data, test energy consumption data and packaging energy consumption data. Among them, the wafer processing energy consumption data is the power consumption data of the wafer processing process, the oxidation energy consumption data is the power consumption data of the oxidation process, the lithography energy consumption data is the power consumption data of the lithography process, the etching energy consumption data is the power consumption data of the etching process, the thin film deposition energy consumption data is the power consumption data of the thin film deposition process, the interconnection energy consumption data is the power consumption data of the interconnection process, the test energy consumption data is the power consumption data of the test process, and the packaging energy consumption data is the power consumption data of the packaging process.

[0036] Specifically, according to the energy consumption in the actual production process, the electricity consumption data and non-electricity consumption data of different production process flows are collected. The non-electricity consumption data includes the consumption of fuel oil and gas. Then, according to the energy characteristics, the carbon emission sources of each link are identified. The electricity consumption data in the carbon emission source is taken as the current energy consumption data. Different manufacturing processes have different current energy consumption data. The current energy consumption data corresponding to each manufacturing process is collected.

[0037] For example, Figure 2 is an example display diagram of current energy consumption data in the semiconductor industry chain provided by the first embodiment of the present invention, such as Figure 2 As shown, the energy consumption data of wafer processing, oxidation energy consumption data of oxidation process, lithography energy consumption data of lithography process, etching energy consumption data of etching process, thin film deposition energy consumption data of thin film deposition process, interconnection energy consumption data of interconnection process, test energy consumption data of test process, and packaging energy consumption data of packaging process are obtained. Among them, since the wafer processing and oxidation process links have high demand for thermal energy, electric energy is used as auxiliary, and thermal energy is generated by electric energy, therefore, the current power consumption data of wafer processing and oxidation are more, accounting for 53%. Lithography and etching have high demand for cold energy, electric energy is used as auxiliary, and cold energy is generated by electric energy, therefore, the current power consumption data of lithography and etching are more, accounting for 24%. Thin film deposition and interconnection have high requirements for power quality, but only use electric energy, therefore, the current power consumption data is less, accounting for 13%. Testing and packaging have high requirements for power quality, but only use electric energy, therefore, the current power consumption data is less, accounting for 10%.

[0038] S102: extract data features from each current energy consumption data to obtain current data features of the current energy consumption data.

[0039] In this embodiment, the current data characteristics can be understood as the characteristic information of the current energy consumption data, that is, the energy characteristics, such as the load data sub-column elements. The load data sub-column elements refer to a series of numerical values ​​or indicators related to the power load in a specific time period in the power system, that is, the load value (power consumption data value).

[0040] Specifically, the current energy consumption data are arranged based on the time series of each current energy consumption data, an energy consumption data set containing multiple time nodes is constructed and merged to fit the corresponding energy consumption load curve, and the load curve is subjected to dimensionality reduction processing to obtain a preset number of load segments and aggregated energy consumption data corresponding to each load segment. When the aggregated energy consumption data meets specific conditions, the current energy consumption data is subjected to segmented aggregation approximation processing based on the aggregated energy consumption data to obtain the current data features.

[0041] S103. Determine the current carbon emissions of the current semiconductor production chain during the production process based on current data characteristics and historical carbon emissions.

[0042] In this embodiment, the historical carbon emissions can be understood as the carbon emissions data of the semiconductor production chain in the historical time. The current carbon emissions can be understood as the carbon emissions data of the semiconductor production chain at the current time.

[0043] Specifically, the carbon emission fitting coefficient is calculated based on the current data characteristics and historical carbon emissions. The current energy consumption data is used as the independent variable, and the current carbon emissions are used as the dependent variable. A carbon emissions calculation model is established according to the carbon emission fitting coefficient. The current energy consumption data is input into the carbon emissions calculation model. The current carbon emissions of the current semiconductor production chain in the production process are calculated through the carbon emissions calculation model.

[0044] The embodiment of the present invention provides a method for calculating carbon emissions that takes into account the energy characteristics of the semiconductor industry chain, including obtaining multiple current energy consumption data of the current semiconductor production chain during the production process; extracting data features of each current energy consumption data to obtain the current data features of the current energy consumption data; and determining the current carbon emissions of the current semiconductor production chain during the production process based on the current data features and historical carbon emissions. The above technical solution can accurately calculate the carbon emissions of the production process on the semiconductor production chain, which helps to constrain producers to formulate production plans based on carbon emissions, achieve energy conservation and emission reduction, and realize the diversification, efficiency, quality and cleanliness of energy supply in industrial agglomeration areas.

[0045] Embodiment 2

[0046] Figure 3 It is a flow chart of a method for calculating carbon emissions taking into account the energy characteristics of the semiconductor industry chain provided in the second embodiment of the present invention. This embodiment is a further optimization of any of the above embodiments and can be applied to situations where carbon emissions are calculated based on the current energy consumption data of each manufacturing process in the semiconductor production process. The method can be executed by a carbon emissions calculation device taking into account the energy characteristics of the semiconductor industry chain. The carbon emissions calculation device taking into account the energy characteristics of the semiconductor industry chain can be implemented in the form of hardware and / or software.

[0047] like Figure 3 As shown, the method includes:

[0048] S201. Obtain multiple current energy consumption data of the current semiconductor production chain during the production process.

[0049] S202: Perform data dimension reduction processing on the current energy consumption data based on the time series of each current energy consumption data to obtain a preset number of aggregated energy consumption data.

[0050] In this embodiment, the aggregated energy consumption data may be understood as an energy consumption average value formed by reducing the dimension and aggregating a number of current energy consumption data.

[0051] Specifically, within the current time period, for each production process, the current energy consumption data of multiple different time nodes in the production process are sorted in chronological order to obtain a time series of each current energy consumption data; based on the time series, a data dimensionality reduction process is performed on several adjacent current energy consumption data to obtain the aggregated energy consumption data corresponding to these current energy consumption data, and a total of a preset number of aggregated energy consumption data are obtained.

[0052] Optionally, based on the time series of each current energy consumption data, data dimension reduction processing is performed on the current energy consumption data to obtain a preset number of aggregated energy consumption data, including:

[0053] S2021. Form a first energy consumption data set based on each current energy consumption data, and fit a corresponding load data curve based on a time series of each current energy consumption data.

[0054] In this embodiment, the first energy consumption data set can be understood as a set of current energy consumption data arranged and combined in chronological order. The load data curve can be understood as the first energy consumption data set in the form of a curve.

[0055] Specifically, the current energy consumption data are sorted according to the collection time, and the n current energy consumption data collected at n time points are combined to form a first energy consumption data set X = [x1 x1 x n ], and use time as the horizontal axis and the data value of the energy consumption data as the vertical axis to fit the first energy consumption data set to form a corresponding load data curve.

[0056] S2022. Perform dimensionality reduction processing on the load data curve to obtain a preset number of load segments, and obtain a corresponding number of aggregated energy consumption data based on the preset number of load segments.

[0057] In this embodiment, the load segment can be understood as a partial segment of the load data curve.

[0058] In this embodiment, the time series symbolic aggregation approximation algorithm (Symbolic Aggregate Approximation, SAX) is used to reduce the dimension of the load data curve and extract features, and a complete load data curve is divided into a preset number of w load segments. The mean of the current energy consumption data contained in each load segment is the aggregated energy consumption data, and accordingly, w aggregated energy consumption data are obtained. As shown, the n-dimensional original time series vector is divided into w segments, thus reducing it to w dimensions, x j is the column vector of the load data curve, that is, the column vector of the first energy consumption data set, is the mean of the ith segment, i.e., the aggregated energy consumption data, is the compression rate. The higher the compression rate, the more obvious the subsequent segmented aggregation effect is, the more precise the fitted carbon emission fitting coefficient is, and the more accurate the carbon emission measurement is.

[0059] S2023. Form a second energy usage data set based on each aggregated energy usage data, wherein both the first energy usage data set and the second energy usage data set satisfy set constraints.

[0060] In this embodiment, the second energy consumption data set can be understood as a set formed by arranging and combining aggregated energy consumption curves in chronological order. Setting constraint conditions can be understood as conditions set for the distance metric of each energy consumption data included in the energy consumption data set to avoid data omission.

[0061] Specifically, The w aggregated energy consumption data are combined to form a second energy consumption data set.

[0062] Specifically, when the load data curve (the first energy consumption data set) is reduced in dimension, the problem of missing reports is prone to occur in the feature space query; the lower bound theorem is used to ensure no missing reports, which is extended to SAX, and the n-dimensional time series Q and C are converted into w-dimensional vectors to obtain PAA representation, and the distance metric formula is used The distance metric constraint between energy consumption data is calculated, where: are the time series after dimension reduction of Q and C, They are The ith element of .

[0063] Exemplarily, whether it is the n-dimensional time series of the first energy usage data set or the w-dimensional time series of the second energy usage data set, the i-th element in the time series Q and the i-th element in the time series C satisfy a certain distance measurement value.

[0064] S203: Perform segmented aggregation approximation processing on the current energy consumption data based on the aggregated energy consumption data to obtain current data features.

[0065] In this embodiment, based on the premise judgment of performing piecewise aggregate approximation processing on aggregated energy consumption data, if the conditions for piecewise aggregate approximation processing are met, the corresponding current energy consumption data in the first energy consumption data set is represented by piecewise aggregate approximation processing (PAA) as the current data feature.

[0066] Optionally, the current energy consumption data is subjected to segmented aggregation approximation processing based on the aggregated energy consumption data to obtain current data features, including:

[0067] S2031. Compare the data value of the aggregated energy consumption data with a preset probability value threshold to obtain a comparison result.

[0068] In this embodiment, the comparison result can be understood as the relative size relationship between the data value of the aggregated energy consumption data and the probability value threshold. The probability value threshold includes a maximum probability value and a minimum probability value.

[0069] Specifically, take the corresponding j-1th probability value β in the Gaussian distribution breakpoint list j-1 As the minimum probability value, the jth probability value is β j is the maximum probability value. and the maximum probability value β j and the minimum probability value β j-1 Perform a comparison and obtain a comparison result.

[0070] S2032: When the comparison result satisfies the aggregation condition, perform segmented aggregation approximation processing on the current energy consumption data in the first energy consumption data set to obtain aggregated current data features.

[0071] In this embodiment, the aggregation condition can be understood as a prerequisite for performing segmented aggregation approximation, for example, the data value of the aggregated energy usage data is greater than the minimum probability value and less than the maximum probability value.

[0072] Specifically, when the comparison result is When the aggregation condition is satisfied, the i-th current energy consumption data x in the first energy consumption data set is determined. i Perform data characterization processing, normalize the data after data characterization processing to obtain the target data α i ,pass Perform a segmented aggregation approximation on the data to obtain the load data sub-column elements That is, the current data characteristics. It is a sub-column element of length n, which is the same as the number of time series.

[0073] S204. Determine a carbon emission fitting coefficient based on current data characteristics and historical carbon emissions.

[0074] In this embodiment, the carbon emission fitting coefficient is an important factor in fitting the carbon emission calculation model. The more accurate the carbon emission fitting coefficient is, the more accurate the carbon emission calculation model is in calculating carbon emissions.

[0075] Specifically, based on the current data characteristics and historical carbon emissions Y i ,pass Calculate the carbon emission fitting coefficient a i , a total of n carbon emission fitting coefficients a1-a are calculated n , where is the mean of the feature sequence composed of each current data feature, is the variance of the feature sequence, is the mean of the carbon emission sequence composed of each historical carbon emission, σ Y is the variance of the carbon emission series.

[0076] S205. Establish a carbon emission calculation model based on the carbon emission fitting coefficient.

[0077] In this embodiment, the carbon emission calculation model can be understood as a model used to calculate carbon emissions. The input of the carbon emission calculation model is the current energy consumption data, and the output is the current carbon emissions.

[0078] Specifically, the least squares method is used to fit the relationship between carbon emissions and energy consumption data. According to n carbon emission fitting coefficients a1-a n Constructing a carbon emissions calculation model Among them, C is the total carbon emissions, which is the dependent variable involved in the fitting; E e is the energy consumption data, which is the independent variable involved in the fitting. n carbon emission fitting coefficients correspond to n energy consumption data E1-E n .

[0079] It is understandable that wafer processing and oxidation are similar processes. Therefore, the same carbon emission calculation model can be established for the processes of wafer processing and oxidation. Similarly, the same carbon emission calculation model can be established for lithography and etching, the same carbon emission calculation model can be established for thin film deposition and interconnection, and the same carbon emission calculation model can be established for testing and packaging.

[0080] At this point, only four carbon emission measurement models need to be established to complete the carbon emission calculation of all manufacturing processes in the semiconductor production chain, effectively improving the efficiency of carbon emission calculation and reducing calculation complexity.

[0081] S206. Input the current energy consumption data into the carbon emission calculation model to obtain the current carbon emissions of the current semiconductor production chain during the production process.

[0082] Specifically, each process has a corresponding carbon emission calculation model. The current energy consumption data collected in a production process is input into the corresponding carbon emission calculation model to obtain the current carbon emission of the process output by the model. The sum of the current carbon emissions of the eight processes is the overall carbon emissions of the production chain in the semiconductor industry chain.

[0083] For example, Figure 4 is an example display diagram of the current carbon emissions in the semiconductor industry chain provided by the second embodiment of the present invention, such as Figure 4 As shown, the total current electricity consumption data (load) of wafer processing and oxidation is 20.54MWh. After inputting it into the carbon emission calculation model corresponding to the wafer processing and oxidation process, the current carbon emissions output by the model are 18.2806 tons; the total current electricity consumption data (load) of lithography and etching is 9.17MWh. After inputting it into the carbon emission calculation model corresponding to the lithography and etching process, the current carbon emissions output by the model are 6.9692 tons; the total current electricity consumption data (load) of thin film deposition and interconnection is 5.125MWh. After inputting it into the carbon emission calculation model corresponding to the thin film deposition and interconnection process, the current carbon emissions output by the model are 3.5875 tons; the total current electricity consumption data (load) of testing and packaging is 3.7MWh. After inputting it into the carbon emission calculation model corresponding to the testing and packaging process, the current carbon emissions output by the model are 2.405 tons.

[0084] The embodiment of the present invention provides a method for calculating carbon emissions that takes into account the energy characteristics of the semiconductor industry chain, including obtaining multiple current energy consumption data of the current semiconductor production chain in the production process; performing data dimension reduction processing on the current energy consumption data based on the time series of each current energy consumption data to obtain a preset number of aggregated energy consumption data; performing segmented aggregation approximation processing on the current energy consumption data based on the aggregated energy consumption data to obtain the current data characteristics; determining the carbon emission fitting coefficient based on the current data characteristics and historical carbon emissions; establishing a carbon emission calculation model based on the carbon emission fitting coefficient; inputting the current energy consumption data into the carbon emission calculation model to obtain the current carbon emissions of the current semiconductor production chain in the production process. The above technical solution can accurately calculate the carbon emissions of the production process on the semiconductor production chain, which helps to constrain producers to formulate production plans based on carbon emissions, achieve energy conservation and emission reduction, and realize the diversification, efficiency, quality and cleanliness of energy supply in industrial agglomeration areas.

[0085] Embodiment 3

[0086] Figure 5 Schematic diagram of a carbon emission calculation device considering the energy characteristics of the semiconductor industry chain provided by the third embodiment of the present invention. Figure 5 As shown, the device comprises:

[0087] The data acquisition module 31 is used to acquire a plurality of current energy consumption data of the current semiconductor production chain during the production process;

[0088] A feature extraction module 32 is used to extract data features from each of the current energy usage data to obtain current data features of the current energy usage data;

[0089] The carbon emission calculation module 33 is used to determine the current carbon emissions of the current semiconductor production chain during the production process based on the current data characteristics and historical carbon emissions.

[0090] The carbon emissions calculation device adopted in this technical solution takes into account the energy characteristics of the semiconductor industry chain. It can accurately calculate the carbon emissions of the production process in the semiconductor production chain, which helps to constrain producers to formulate production plans based on carbon emissions, achieve energy conservation and emission reduction, and realize the diversification, efficiency, quality and cleanliness of energy supply in industrial agglomeration areas.

[0091] Optionally, the feature extraction module 32 includes:

[0092] A data dimension reduction unit, configured to perform data dimension reduction processing on the current energy consumption data based on the time series of each current energy consumption data to obtain a preset number of aggregated energy consumption data;

[0093] The segmented aggregation unit is used to perform segmented aggregation approximation processing on the current energy consumption data based on the aggregated energy consumption data to obtain current data features.

[0094] Optional, data dimension reduction unit, specifically used for:

[0095] forming a first energy usage data set based on each of the current energy usage data, and fitting a corresponding load data curve based on a time series of each of the current energy usage data;

[0096] Performing dimensionality reduction processing on the load data curve to obtain a preset number of load segments, and obtaining a corresponding number of aggregated energy consumption data according to the preset number of load segments;

[0097] A second energy usage data set is formed based on each of the aggregated energy usage data, wherein both the first energy usage data set and the second energy usage data set satisfy set constraints.

[0098] Optional, segment aggregation unit, specifically used for:

[0099] Comparing the data value of the aggregated energy consumption data with a preset probability value threshold to obtain a comparison result;

[0100] When the comparison result satisfies the aggregation condition, segmented aggregation approximation processing is performed on the current energy consumption data in the first energy consumption data set to obtain aggregated current data features.

[0101] Optionally, the carbon emission calculation module 33 is specifically used for:

[0102] Determining a carbon emission fitting coefficient based on the current data characteristics and the historical carbon emissions;

[0103] Establishing a carbon emission calculation model according to the carbon emission fitting coefficient;

[0104] The current energy consumption data is input into the carbon emission calculation model to obtain the current carbon emissions of the current semiconductor production chain during the production process.

[0105] Optionally, the current energy consumption data includes at least: wafer processing energy consumption data, oxidation energy consumption data, lithography energy consumption data, etching energy consumption data, thin film deposition energy consumption data, interconnection energy consumption data, test energy consumption data and packaging energy consumption data.

[0106] The carbon emissions calculation device considering the energy characteristics of the semiconductor industry chain provided in an embodiment of the present invention can execute the carbon emissions calculation method considering the energy characteristics of the semiconductor industry chain provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0107] Embodiment 4

[0108] Figure 6 : is a structural schematic diagram of an electronic device provided in Embodiment 4 of the present invention. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0109] like Figure 6As shown, the electronic device 40 includes at least one processor 41, and a memory connected to the at least one processor 41, such as a read-only memory (ROM) 42, a random access memory (RAM) 43, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 41 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 42 or the computer program loaded from the storage unit 48 to the random access memory (RAM) 43. In the RAM 43, various programs and data required for the operation of the electronic device 40 can also be stored. The processor 41, the ROM 42, and the RAM 43 are connected to each other through a bus 44. An input / output (I / O) interface 45 is also connected to the bus 44.

[0110] A number of components in the electronic device 40 are connected to the I / O interface 45, including: an input unit 46, such as a keyboard, a mouse, etc.; an output unit 47, such as various types of displays, speakers, etc.; a storage unit 48, such as a disk, an optical disk, etc.; and a communication unit 49, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 49 allows the electronic device 40 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0111] The processor 41 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 41 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The processor 41 executes the various methods and processes described above, such as a carbon emissions calculation method considering the energy characteristics of the semiconductor industry chain.

[0112] In some embodiments, the carbon emissions calculation method considering the energy characteristics of the semiconductor industry chain can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 48. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 40 via the ROM 42 and / or the communication unit 49. When the computer program is loaded into the RAM 43 and executed by the processor 41, one or more steps of the carbon emissions calculation method considering the energy characteristics of the semiconductor industry chain described above can be performed. Alternatively, in other embodiments, the processor 41 can be configured to execute the carbon emissions calculation method considering the energy characteristics of the semiconductor industry chain by any other appropriate means (for example, by means of firmware).

[0113] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0114] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0115] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0116] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0117] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0118] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0119] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0120] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for calculating carbon emissions taking into account the energy characteristics of the semiconductor industry chain, characterized in that: include: Obtain multiple current energy consumption data of the current semiconductor production chain during the production process; Extracting data features from each of the current energy usage data to obtain current data features of the current energy usage data; Based on the current data characteristics and historical carbon emissions, the current carbon emissions of the current semiconductor production chain during the production process are determined.

2. The method according to claim 1, characterized in that Extracting data features from each of the current energy usage data to obtain current data features of the current energy usage data includes: Performing data dimension reduction processing on the current energy consumption data based on the time series of each current energy consumption data to obtain a preset number of aggregated energy consumption data; The current energy consumption data is subjected to segmented aggregation approximation processing based on the aggregated energy consumption data to obtain current data features.

3. The method according to claim 2, characterized in that Performing data dimension reduction processing on the current energy consumption data based on the time series of each current energy consumption data to obtain a preset number of aggregated energy consumption data, including: forming a first energy usage data set based on each of the current energy usage data, and fitting a corresponding load data curve based on a time series of each of the current energy usage data; Performing dimensionality reduction processing on the load data curve to obtain a preset number of load segments, and obtaining a corresponding number of aggregated energy consumption data according to the preset number of load segments; A second energy usage data set is formed based on each of the aggregated energy usage data, wherein both the first energy usage data set and the second energy usage data set satisfy set constraints.

4. The method according to claim 3, characterized in that The current energy consumption data is subjected to segmented aggregation approximation processing based on the aggregated energy consumption data to obtain current data features, including: Comparing the data value of the aggregated energy consumption data with a preset probability value threshold to obtain a comparison result; When the comparison result satisfies the aggregation condition, segmented aggregation approximation processing is performed on the current energy consumption data in the first energy consumption data set to obtain aggregated current data features.

5. The method according to claim 1, characterized in that Based on the current data characteristics and historical carbon emissions, determine the current carbon emissions of the current semiconductor production chain during the production process, including: Determining a carbon emission fitting coefficient based on the current data characteristics and the historical carbon emissions; Establishing a carbon emission calculation model according to the carbon emission fitting coefficient; The current energy consumption data is input into the carbon emission calculation model to obtain the current carbon emissions of the current semiconductor production chain during the production process.

6. The method according to claim 1, characterized in that The current energy consumption data at least includes: wafer processing energy consumption data, oxidation energy consumption data, lithography energy consumption data, etching energy consumption data, thin film deposition energy consumption data, interconnection energy consumption data, testing energy consumption data and packaging energy consumption data.

Images