Carbon loadability collaborative optimization and abnormality attribution method, device, storage medium and product

Abstract

This application discloses a method, device, storage medium, and product for coordinated optimization of energy and carbon load and anomaly attribution, belonging to the field of energy and production coordinated management and control technology. This application uses the intersection ratio of planned execution period and metering period as the energy consumption allocation weight to achieve precise correlation between production tasks and energy metering; it generates a load baseline by integrating the current scheduled task load with the measured load of the previous period and calculates the energy and carbon anomaly degree, enabling load forecasting to respond to scheduling changes and reflect both deviations in energy consumption and carbon emissions; it identifies flexible and rigid loads and generates scheduling strategies based on multi-objective scoring, taking into account peak shaving, cost reduction, carbon reduction, and on-time delivery; it determines the contribution of causes through energy and carbon anomalies and updates the energy consumption baseline in a closed loop, connecting anomaly detection, cause location, scheduling execution, and model updates, thereby solving the problems of energy and scheduling separation, forecasting driven by missing processes, difficulty in optimizing while considering energy and carbon objectives, difficulty in anomaly location, and difficulty in feedback on handling.

Description

Technical Field

[0001] This application relates to the field of energy and production collaborative management technology, and in particular to energy and carbon load collaborative optimization and anomaly attribution methods, equipment, storage media and products. Background Technology

[0002] In the digital management of manufacturing plants, subsystems such as production scheduling systems and energy management systems have data acquisition capabilities. However, because each system stores data in a decentralized manner according to its own boundaries, energy consumption is difficult to accurately be attributed to the production task dimension. Existing load forecasts rely on historical total trends, which are difficult to reflect the impact of scheduling changes and process combinations. Production scheduling and energy optimization objectives are inconsistent, and there is a lack of a unified energy and carbon co-optimization method. When energy consumption is abnormal, only metering point alarms can be output, and it is impossible to locate the cause in the process or equipment. The results of energy-saving measures are also difficult to be fed back to update model parameters to form continuous optimization. Summary of the Invention

[0003] To address the problems of disconnect between energy data and production scheduling, inconsistency between energy and carbon optimization and scheduling objectives, difficulty in locating energy consumption anomalies, and difficulty in providing feedback on handling results in manufacturing plants, this application provides a method, device, storage medium, and product for coordinated optimization of energy and carbon load and anomaly attribution, so as to achieve accurate correlation between production tasks and energy metering, coordinated optimization of energy and carbon load, and continuous updating of energy consumption baseline.

[0004] This application provides a method for coordinated optimization of energy and carbon loads and anomaly attribution, including:

[0005] Obtain production tasks and energy metering records, and establish a time correlation between the production tasks and the energy metering records, wherein the ratio of the intersection length of the planned execution period and the metering period to the length of the metering period is used as the energy consumption allocation weight.

[0006] Calculate task-level energy consumption and carbon emissions based on the energy consumption allocation weights;

[0007] A load baseline is generated based on the current scheduled task load and the measured load of the previous period. The energy and carbon anomaly is calculated based on the load deviation and carbon emission deviation.

[0008] Identify flexible and rigid loads, and generate multi-objective scheduling optimization strategies based on flexible load capacity and process constraints;

[0009] Based on the energy and carbon anomaly degree, determine the contribution of the anomaly cause, implement measures, and update the energy consumption baseline.

[0010] Optionally, the step of acquiring production tasks and energy metering records, and establishing a time correlation between the production tasks and the energy metering records, includes:

[0011] Obtain production tasks containing execution equipment identifiers and planned time windows from the production scheduling system, and obtain metering records containing metering equipment identifiers and sampling time windows from the energy management system;

[0012] The execution device identifier is matched with the metering device identifier, and the planned time window is intersected with the sampling time window. For production tasks and metering records that simultaneously meet the conditions of device matching and time window intersection, the ratio of the intersection length of the planned time window and the sampling time window to the total length of the sampling time window is calculated and used as the energy consumption allocation weight.

[0013] Optionally, the calculation of task-level energy consumption and carbon emissions based on the energy consumption allocation weight includes:

[0014] Based on the energy consumption allocation weight, the energy consumption value of each metering record, and the conversion factor corresponding to each energy type, the energy consumption of different metering units is converted to a unified energy caliber, and the task-level standard energy consumption is obtained by summarizing.

[0015] Based on the energy consumption allocation weight, the energy consumption value of each metering record, and the carbon emission factor corresponding to each energy type in each energy consumption period, the task-level carbon emissions are calculated.

[0016] Optionally, generating a load baseline based on the current scheduled task load and the measured load of the previous time period includes:

[0017] The standard load of the planned production tasks in the current schedule is summarized by time period. Combined with the measured load of the previous time period, the sum of the measured load and the standard load is weighted and fused according to a preset smoothing coefficient to generate the load baseline.

[0018] Optionally, the calculation of energy carbon anomaly based on load deviation and carbon emission deviation includes:

[0019] The load deviation is obtained by comparing the measured load during the time period with the load baseline, and the carbon emission deviation is obtained by comparing the total carbon emission value of the task during the time period with the historical carbon emission baseline.

[0020] The energy-carbon anomaly is obtained by adding the ratio of the absolute value of the load deviation to the sum of the load baseline and the preset constant, and the ratio of the absolute value of the carbon emission deviation to the sum of the historical carbon emission baseline and the preset constant.

[0021] Optionally, the identification of flexible loads and rigid loads includes:

[0022] Based on process attributes, the scheduling tasks are identified as flexible loads, including drying, heat treatment auxiliary section, air compressor station loading, energy storage charging and discharging, and non-critical test auxiliary loads, while critical processes that affect product quality continuity are identified as rigid loads.

[0023] Optionally, the multi-objective scheduling optimization strategy generated based on flexible load capacity and process constraints includes:

[0024] Calculate the adjustable capacity of flexible load for each time period, generate candidate scheduling strategies based on the adjustable capacity of flexible load and process constraints, sum the normalized peak load value, normalized time-of-use energy cost value, normalized time-of-use carbon emission value and normalized delivery deviation value of the candidate scheduling strategies to obtain a score, and select the candidate scheduling strategy with the smallest score as the multi-objective scheduling optimization strategy.

[0025] This application provides an electronic device, the electronic device comprising:

[0026] One or more processors; and

[0027] A memory storing computer program instructions, which, when executed, cause the processor to perform the steps of the above method.

[0028] This application provides a computer-readable storage medium having a computer program / instructions stored thereon, which, when executed by a processor, implement the steps of the above-described method.

[0029] This application provides a computer program product, including a computer program / instructions that, when executed by a processor, implement the steps of the above-described method.

[0030] The beneficial effects of the above technical solution are as follows:

[0031] In this technical solution, the energy and carbon load collaborative optimization and anomaly attribution method of this application uses the ratio of the intersection length of the planned execution period and the metering period to the length of the metering period as the energy consumption allocation weight to achieve accurate correlation between production tasks and energy metering records, transforming energy data from the metering point dimension into task-level computable data; by combining the current scheduled task load and the measured load of the previous period to generate a load baseline and calculate the energy and carbon anomaly degree, the load forecast can respond to schedule changes and simultaneously reflect deviations in both energy and carbon emission dimensions; by identifying flexible loads and rigid loads and generating scheduling optimization strategies based on a multi-objective scoring model, multiple objectives such as peak shaving, cost reduction, carbon reduction, and on-time delivery are taken into account without disrupting process and delivery constraints; by determining the contribution of anomaly causes based on the energy and carbon anomaly degree and executing actions to update the energy consumption baseline, anomaly detection, cause location, scheduling execution, and model update are connected into a continuous optimization closed loop, thereby solving the problems of energy data being separated from production schedules, load forecasting lacking process-driven approaches, scheduling optimization being unable to take energy and carbon objectives into account, difficulty in locating the causes of anomalies, and difficulty in feeding energy-saving actions back to the model. Attached Figure Description

[0032] One or more embodiments are illustrated by way of example with reference numerals in the accompanying drawings. These illustrations do not constitute a limitation on the embodiments. Elements with the same reference numerals in the drawings are denoted as similar elements. Unless otherwise stated, the figures in the drawings are not to be limited by scale.

[0033] Figure 1 This is a flowchart of one embodiment of the energy and carbon load co-optimization and anomaly attribution method described in this application;

[0034] Figure 2 A flowchart of a method for determining the energy consumption allocation weight in this application;

[0035] Figure 3 This is a flowchart illustrating an embodiment of the method for calculating task-level energy consumption and carbon emissions according to this application.

[0036] Figure 4 This is a flowchart of a method for determining the contribution of anomalies to energy and carbon anomalies and updating the energy consumption baseline according to an embodiment of this application;

[0037] Figure 5 This is an exemplary structural diagram of an electronic device according to this application. Detailed Implementation

[0038] The advantages of this application are further illustrated below with reference to the accompanying drawings and specific embodiments.

[0039] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0040] The terminology used in this application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. The singular forms “a,” “the,” and “the” used in this application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any or all possible combinations of one or more of the associated listed items.

[0041] It should be understood that although the terms first, second, third, etc., may be used in this application to describe various information, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, without departing from the scope of this application, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the word "if" as used herein may be interpreted as "when," "when," or "in response to determination."

[0042] In the description of this application, it should be understood that the numerical labels before the steps do not indicate the order of the steps, but are only used to facilitate the description of this application and to distinguish each step, and therefore should not be construed as a limitation of this application.

[0043] The method described in this application can be deployed in the energy management platform, production scheduling system, industrial big data platform, or park-level energy and carbon management system of a manufacturing plant, and can be applied to discrete manufacturing scenarios such as power equipment manufacturing, rail transit vehicle manufacturing, air conditioning and home appliance manufacturing, and steel and metal processing.

[0044] The method described in this application can be applied not only to power equipment manufacturing plants, such as the manufacturing processes of transformers, switchgear, instrument transformers, cable accessories, and protection devices, but also to any manufacturing scenario requiring coordinated management of multiple types of energy consumption and production scheduling, such as chemical process manufacturing, food processing, textile printing and dyeing, and automotive parts manufacturing. This application uses a power equipment manufacturing plant as an example, but it is not limited to this.

[0045] In this embodiment, the production task data collected by the Manufacturing Execution System (MAS), the metering record data collected by the Energy Management System (EMS), and the equipment operating status data collected by the Equipment Status Acquisition Platform (ESAP) are processed by the Energy and Carbon Load Co-optimization System to generate energy and carbon accounting results, load baseline predictions, energy and carbon anomaly degrees, scheduling optimization strategies, and anomaly cause attribution results. The system then feeds back scheduling adjustment instructions to the production scheduling system and issues anomaly handling tasks to the EMS and EMS. Simultaneously, the updated energy consumption baseline is used for subsequent scheduling optimization. The winding workshop, drying workshop, impregnation workshop, heat treatment workshop, and painting line of Manufacturing Plant A transmit metering data from electricity meters, gas meters, steam meters, and compressed air meters to the EMS via fieldbus. The MAS synchronizes the production task and process plan data of each workshop to the production scheduling system. The Energy and Carbon Load Co-optimization System obtains the above data from the production scheduling system and the EMS, performs energy and carbon load co-optimization and anomaly attribution processing, and issues the generated scheduling adjustment instructions and anomaly handling tasks to the corresponding workshops for execution.

[0046] This application proposes a method for coordinated optimization of energy and carbon loads and attribution of anomalies to address existing problems such as the disconnect between energy data and production scheduling, the lack of process-driven load forecasting, the difficulty in balancing energy and carbon targets in scheduling optimization, the difficulty in locating the causes of energy consumption anomalies, and the lack of feedback models for energy-saving measures. (See reference...) Figure 1 This is a flowchart illustrating a preferred embodiment of the energy and carbon load co-optimization and anomaly attribution method according to this application. As can be seen from the figure, the energy and carbon load co-optimization and anomaly attribution method provided in this embodiment mainly includes the following steps:

[0047] S1. Obtain production tasks and energy metering records, and establish a time correlation between the production tasks and the energy metering records, wherein the ratio of the intersection length of the planned execution period and the metering period to the length of the metering period is used as the energy consumption allocation weight.

[0048] S2. Calculate task-level energy consumption and carbon emissions based on the energy consumption allocation weights;

[0049] S3. Generate a load baseline based on the current scheduled task load and the measured load of the previous period, and calculate the energy and carbon anomaly degree based on the load deviation and carbon emission deviation.

[0050] S4. Identify flexible and rigid loads, and generate multi-objective scheduling optimization strategies based on flexible load capacity and process constraints;

[0051] S5. Determine the contribution of the cause of the anomaly based on the energy and carbon anomaly, perform the action, and update the energy consumption baseline.

[0052] In this embodiment, the energy and carbon load collaborative optimization and anomaly attribution method uses the ratio of the intersection length of the planned execution period and the metering period to the length of the metering period as the energy consumption allocation weight, thereby achieving a precise correlation between production tasks and energy metering records and transforming energy data from the metering point dimension into task-level computable data. By combining the current scheduled task load and the measured load of the previous period to generate a load baseline and calculate the energy and carbon anomaly degree, the load forecast can respond to schedule changes and simultaneously reflect deviations in both energy and carbon emission dimensions. By identifying flexible and rigid loads and generating scheduling optimization strategies based on a multi-objective scoring model, the method balances multiple objectives such as peak shaving, cost reduction, carbon reduction, and on-time delivery without compromising process and delivery constraints. By determining the contribution of anomaly causes based on the energy and carbon anomaly degree and implementing measures to update the energy consumption baseline, the method connects anomaly detection, cause location, scheduling execution, and model update into a continuous optimization closed loop. This solves the problems of energy data being separated from production scheduling, lack of process-driven load forecasting, difficulty in balancing energy and carbon objectives in scheduling optimization, difficulty in locating the causes of anomalies, and difficulty in feeding energy-saving measures back to the model.

[0053] In an optional embodiment, step S1 involves acquiring production tasks and energy metering records, and establishing a time correlation between the production tasks and the energy metering records, such as... Figure 2 As shown, the following steps may be included:

[0054] S11. Obtain production tasks containing execution equipment identifiers and planned time windows from the production scheduling system, and obtain metering records containing metering equipment identifiers and sampling time windows from the energy management system;

[0055] S12. Match the execution equipment identifier with the metering equipment identifier, and determine the intersection of the planned time window and the sampling time window. For production tasks and metering records that simultaneously meet the conditions of equipment matching and time window intersection, calculate the ratio of the intersection length of the planned time window and the sampling time window to the total length of the sampling time window, and use it as the energy consumption allocation weight.

[0056] In this embodiment, data is obtained from the production scheduling system and the energy management system, respectively. A production task includes an execution device identifier and a planned time window, determined by the start and end times of the production task. An energy metering record includes a metering device identifier and a sampling time window, determined by the sampling start time and sampling duration of the metering record. First, the execution device identifier is matched with the metering device identifier to filter out tasks and metering records corresponding to the same device. Then, the planned time window and the sampling time window are compared for intersection, retaining only record pairs where the time windows intersect. For record pairs that simultaneously meet the device matching and time window intersection conditions, the ratio of the intersection length of the planned time window and the sampling time window to the total length of the sampling time window is calculated, serving as the energy consumption allocation weight for that metering record belonging to the corresponding production task. This weight ranges from 0 to 1; the weight is 1 when the metering record falls completely within the task's time window, the weight is the intersection ratio when there is only partial overlap, and the weight is 0 when there is no overlap. This method can accurately handle complex situations in actual production, such as equipment preheating, shutdown delays, and sampling cycles crossing task boundaries, avoiding energy consumption attribution errors caused by simply classifying the entire metering record into a single task.

[0057] Based on the above steps S11 and S12, the system forms a candidate record set for task-level energy consumption accounting, denoted as Y. i The candidate record set is determined by the execution device d. i Measurement record set with sampling time window and task time window The intersection of the sets of intersecting measurement records is formed as shown in formula (1):

[0058] (1)

[0059] Among them, Y i Represents the set of candidate measurement records for production task i; The execution device is d. i A collection of measurement records; Indicates the sampling time window and the task time window The set of intersecting measurement records. Formula (1) is derived from the equipment matching and time window intersection rules.

[0060] Based on the above candidate record set Y i Further calculate the overlap ratio between each measurement record and the production task time window, for example, formula (2), that is, the time allocation weight. :

[0061] (2)

[0062] in, This indicates the time allocation weight attribution of measurement record j to production task i; a i and b i From the production task time window; t j and h j The formula (2) is derived from the interval overlap rate calculation and ranges from 0 to 1. This ratio is used to address the energy consumption attribution issue caused by the metering cycle crossing task boundaries, equipment preheating, and shutdown delays.

[0063] By using the ratio of the intersection length of the planned execution period and the metering period to the length of the metering period as the energy consumption allocation weight, the embodiments of this application realize the precise association between production tasks and energy metering records based on the original time window. Unlike the existing technology that aligns by segments after unifying the time granularity, this method can complete the precise binding of cross-system data without modifying the original data time granularity.

[0064] In an optional embodiment, step S2 calculates task-level energy consumption and carbon emissions based on the energy consumption allocation weight, such as... Figure 3 The following steps may be included:

[0065] S21. Based on the energy consumption allocation weight, the energy consumption value of each metering record, and the conversion factor corresponding to each energy type, the energy consumption of different metering units is converted to a unified energy caliber, and the task-level standard energy consumption is obtained by summarizing.

[0066] S22. Calculate the task-level carbon emissions based on the energy consumption allocation weight, the energy consumption value of each metering record, and the carbon emission factor corresponding to each energy type in each energy consumption period.

[0067] In this embodiment, after determining the energy consumption allocation weight in step S1, step S21, based on the energy consumption allocation weight, the energy consumption value of each metering record, and the conversion factor corresponding to each energy type, converts the energy consumption of different metering units such as electricity, natural gas, compressed air, steam, and cooling water to a unified energy caliber, and summarizes them to obtain the task-level standard energy consumption. Step S21 uniformly converts the metering units of each energy type into standard energy units (such as standard coal equivalent or kilowatt-hours), enabling horizontal comparison of the consumption of different energy types. Simultaneously, step S22 calculates the task-level carbon emissions based on the energy consumption allocation weight, the energy consumption value of each metering record, and the carbon emission factor corresponding to each energy type in each energy consumption period. For electricity metering records, the time-of-use electricity carbon factor for the energy consumption period is used; for non-electricity energy metering records, the enterprise or industry standard carbon emission factor for the corresponding energy type is used. Both the task-level standard energy consumption and the task-level carbon emissions can be traced back to specific production tasks, processes, equipment, and product families, providing an accurate data foundation for subsequent load forecasting, anomaly detection, and scheduling optimization.

[0068] In step S21, the task-level standard energy consumption E i Calculated using formula (3):

[0069] (3)

[0070] Among them, E i Y represents the standard energy consumption of production task i; i From the candidate record set; B ij Weights are allocated to time; v j This represents the incremental value of metering record j, i.e., the energy consumption value; Indicates energy type e j The coefficient is converted to a uniform energy unit. Formula (3) is derived from the summation (or weighted summation) and energy conversion calculation. The result is used for horizontal comparison between processes, equipment and product families, and also serves as the basis for subsequent load baseline and closed-loop update.

[0071] In step S22, the mission-level carbon emissions C i Calculated using formula (4):

[0072] (4)

[0073] Among them, C i Indicates the carbon emissions of production task i; v j The incremental value is used for measurement, i.e., the energy consumption value; Indicates energy type e j At time t jThe corresponding carbon emission factor. Formula (4) is derived from the carbon accounting method of multiplying activity data by emission factors. By matching carbon emission factors according to energy type and energy consumption period, the carbon emissions traceable to the production task can be obtained.

[0074] In an optional embodiment, step S3 generates a load baseline based on the current scheduled task load and the measured load of the previous time period, including:

[0075] The standard load of the planned production tasks in the current schedule is summarized by time period. Combined with the measured load of the previous time period, the sum of the measured load and the standard load is weighted and fused according to a preset smoothing coefficient to generate the load baseline.

[0076] In this embodiment, step S3 summarizes the standard load of the planned production tasks in the current schedule by time period. The standard load is determined based on historical energy consumption data under the same product family, process, and equipment conditions. The standard load of each task is summed to obtain the theoretical load of the current schedule. Combined with the measured load of the previous time period, the sum of the measured load and the theoretical load is weighted and fused according to a preset smoothing coefficient to generate a short-term load baseline. The smoothing coefficient λ ranges from 0 to 1. When the smoothing coefficient is large, the prediction relies more on the measured value of the previous time period; when the smoothing coefficient is small, the prediction relies more on the theoretical value of the current schedule.

[0077] In step S3, the short-term load baseline Calculated using the exponential smoothing formula (5):

[0078] (5)

[0079] in, The forecast load baseline for time period t is represented by λ, which is the smoothing coefficient ranging from 0 to 1; P t-1 Indicates the measured load of the previous period; A t This represents the set of production tasks planned to be executed within time period t; This represents the standard load of production task i under the same product family, process, and equipment conditions. Formula (5) is derived from exponential smoothing forecasting. By integrating the measured load of the previous period and the standard load of the current scheduled task, the forecast result can change with the production execution status.

[0080] In an optional embodiment, step S3 calculates the energy carbon anomaly based on the load deviation and carbon emission deviation, including:

[0081] The load deviation is obtained by comparing the measured load during the time period with the load baseline, and the carbon emission deviation is obtained by comparing the total carbon emission value of the task during the time period with the historical carbon emission baseline.

[0082] The energy-carbon anomaly is obtained by adding the ratio of the absolute value of the load deviation to the sum of the load baseline and the preset constant, and the ratio of the absolute value of the carbon emission deviation to the sum of the historical carbon emission baseline and the preset constant.

[0083] In this embodiment, the load deviation is obtained by comparing the measured load during a time period with the load baseline, and the carbon emission deviation is obtained by comparing the sum of the task-level carbon emissions of all planned tasks during the time period with the historical carbon emission baseline. The energy-carbon anomaly is obtained by adding the absolute value of the load deviation to the sum of the load baseline plus a preset constant (a very small positive number) to the absolute value of the carbon emission deviation to the sum of the historical carbon emission baseline plus the preset constant. The preset constant is used to avoid the denominator being zero during low-load or shutdown periods. The energy-carbon anomaly reflects the deviation at both the energy consumption and carbon emission levels, and is a two-dimensional fusion anomaly measurement index.

[0084] In step S3, the carbon anomaly Zt is calculated using formula (6):

[0085] (6)

[0086] Where Zt represents the energy-carbon anomaly at time t; P t This represents the measured load during time period t; The predicted load baseline is derived from the above load baseline formula; At is the set of production tasks planned to be executed within time period t; C i From the carbon emission accounting formula; ε represents the historical carbon emission baseline for time period t under the same shift and production structure; ε represents a very small positive number. Formula (6) is derived from the normalized residual calculation, retaining only the two core quantities of load deviation and carbon emission deviation, avoiding the introduction of additional parameters that are irrelevant to subsequent scheduling.

[0087] By combining the current scheduled task load and the measured load of the previous period to generate a load baseline, the embodiments of this application enable load forecasting to respond instantly to scheduling changes (through the standard load of the scheduled task) while maintaining tracking of the actual operating status (through the measured load of the previous period), making it more accurate than pure historical trend forecasting when there are temporary changes in the schedule or fluctuations in equipment status.

[0088] In an optional embodiment, step S4 identifies flexible loads and rigid loads, including:

[0089] Based on process attributes, the scheduling tasks are identified as flexible loads, including drying, heat treatment auxiliary section, air compressor station loading, energy storage charging and discharging, and non-critical test auxiliary loads, while critical processes that affect product quality continuity are identified as rigid loads.

[0090] In this embodiment, flexible and rigid loads are identified from the scheduling tasks based on process attributes. Drying processes, heat treatment auxiliary sections, air compressor station loading, energy storage charging and discharging, and non-critical test auxiliary loads are identified as flexible loads. These processes or auxiliary loads can be adjusted in advance, postpone, or in stages within the time window allowed by the process without affecting product quality. Critical processes that affect the continuity of product quality (such as winding, impregnation, main heat treatment, etc.) are identified as rigid loads. These processes must be executed in a predetermined order and within a predetermined time window.

[0091] In step S4, after identifying the flexible load, the system calculates the adjustable capacity F of the flexible load for each time period. t As shown in formula (7):

[0092] (7)

[0093] Among them, F t The adjustable capacity represents time period t; At represents the set of production tasks planned to be executed within time period t; g i The flexible flag represents production task i, with 1 for flexible tasks and 0 for rigid tasks. Standard load derived from load baseline formula (5); s i This indicates the adjustable proportion of task i within the allowed window of the process. Formula (7) is derived from the flexible load capacity accumulation rule. By filtering the flexible loads that can be executed in advance, postponed, or in segments, the capacity space available for scheduling optimization in each time period is calculated.

[0094] In an optional embodiment, step S4 generates a multi-objective scheduling optimization strategy based on flexible load capacity and process constraints, including:

[0095] Calculate the adjustable capacity of flexible load for each time period, generate candidate scheduling strategies based on the adjustable capacity of flexible load and process constraints, sum the normalized peak load value, normalized time-of-use energy cost value, normalized time-of-use carbon emission value and normalized delivery deviation value of the candidate scheduling strategies to obtain a score, and select the candidate scheduling strategy with the smallest score as the multi-objective scheduling optimization strategy.

[0096] In this embodiment, the adjustable capacity of flexible load for each time period is calculated, that is, the sum of the adjustable capacity is equal to the sum of the products of the standard load of all flexible loads in that time period and their respective adjustable proportions. Based on the adjustable capacity of flexible load and process constraints such as process sequence, equipment capacity, and delivery window, candidate scheduling strategies are generated. The peak load normalized value, time-of-use energy cost normalized value, time-of-use carbon emission normalized value, and delivery deviation normalized value of the candidate scheduling strategies are summed to obtain a comprehensive score. The multi-objective scheduling optimization strategies are output in ascending order of scores. The smaller the score, the better the overall performance of the strategy in peak shaving, cost reduction, carbon reduction, and delivery guarantee. It can be understood that this scoring model can also be adapted to the preferences of different factories for various indicators by configuring different weight coefficients for each normalized value. In this case, formula (8) is extended to a weighted summation of each item.

[0097] In step S4, the score J of the candidate scheduling strategy is... q Calculated using formula (8):

[0098] (8)

[0099] Among them, J q The score represents the candidate scheduling strategy q; P represents the predicted average load of strategy q in time period t; max Indicates the normalized upper limit of peak load; π t Δ represents the energy price during time period t; t M represents the duration of time period t; max Indicates the normalized upper limit of energy costs; φ t The carbon emission factor represents the carbon emission factor for time period t; C max Indicates the normalized upper limit of carbon emissions; D qi D represents the delivery deviation of task i under strategy q; max This represents the upper limit of the normalized delivery deviation. Formula (8) is derived from the multi-objective normalized summation score, where... For energy consumption over a given period, ensure that the dimensions of the cost and carbon emission items are consistent. The lower the score, the more suitable the strategy is for implementation.

[0100] By identifying flexible and rigid loads and generating scheduling optimization strategies based on a four-objective scoring model, the embodiments of this application enable the scheduling scheme to simultaneously meet the multiple needs of grid-side peak shaving, economic-side cost reduction, environmental-side carbon reduction, and production-side delivery assurance without compromising process and delivery time constraints.

[0101] In an optional embodiment, step S5 determines the contribution of the anomaly cause based on the energy and carbon anomaly degree, performs actions, and updates the energy consumption baseline. Specifically, the contribution is first ranked based on the evidence hit rate of candidate causes and the energy and carbon anomaly degree; then, corresponding actions are generated and executed according to the ranking results; finally, the energy consumption baseline is updated according to the execution results. Figure 4 As shown, the following steps may be included:

[0102] S51. A pre-defined candidate cause rule base is used to determine whether the evidence conditions for each candidate cause are met during the corresponding abnormal time period and to generate evidence hit markers.

[0103] S52. The contribution of the candidate cause is obtained by summing the product of the energy and carbon anomaly degree of each anomalous period and the evidence hit mark of the corresponding candidate cause in that period, and then dividing by the sum of the energy and carbon anomalies of all anomalous periods.

[0104] S53. Based on the contribution ranking results, generate at least one of the following tasks and execute it: peak shifting suggestions, equipment inspection, metering verification, energy storage strategy adjustment, or team rectification tasks.

[0105] S54. Divide the difference between the actual energy consumption after execution and the baseline value before the update by the historical sample count, add the quotient to the baseline value before the update, and update the energy consumption baseline for the process, equipment, and product family dimensions.

[0106] In this embodiment, a candidate cause rule base is preset. The candidate causes in the rule base include centralized scheduling start-up, equipment idling, metering point drift, differences in shift operation, and deviation of energy storage strategy. For each candidate cause, it is determined whether its evidence conditions are met in each abnormal period (such as whether there is evidence of centralized scheduling start-up in a certain period), and an evidence hit flag is generated (1 if met, 0 if not met).

[0107] In step S52, the contribution G_r of the candidate cause r is calculated using formula (9):

[0108] (9)

[0109] Among them, G r Z represents the contribution of candidate cause r; T represents the set of anomalous time periods that enter the attribution calculation; t I represents the time-period anomaly degree t derived from the energy and carbon anomaly formula; rt The evidence hit flag for candidate cause r in time period t is 1 if it hits and 0 otherwise. Formula (9) is derived from the weighted proportion calculation of anomaly degree and is used to sort and output the main anomaly causes. The higher the contribution, the greater the impact of the cause on the overall anomaly.

[0110] Based on the contribution ranking results, step S53 generates and executes at least one of the following tasks: peak shifting suggestions, equipment inspection, metering verification, energy storage strategy adjustment, or team rectification. After execution, step S54 divides the difference between the actual energy consumption after execution and the baseline value before the update by the cumulative number of samples n, adds the quotient to the baseline value before the update, and updates the energy consumption baseline and scheduling benefit parameters for the process, equipment, and product family dimensions.

[0111] In step S54, the energy consumption baseline is updated using the incremental mean formula (10):

[0112] (10)

[0113] in, This represents the standard energy consumption average of process p, equipment d, and product family c after the nth closed loop; This represents the average standard energy consumption after the last closed-loop operation; This represents the standard energy consumption for completing the nth task in this dimension, taken from the E values ​​of process, equipment, and product family corresponding to p, d, and c in the task-level standard energy consumption formula. i ; n represents the cumulative number of samples in this dimension. Formula (10) is derived from incremental mean update, which only uses the samples of this task and does not require replaying all historical data, enabling carbon load collaborative optimization, anomaly attribution and execution feedback to form a closed loop.

[0114] By determining the contribution of anomalies based on energy and carbon anomalies and implementing measures to update the energy consumption baseline, this application's embodiments connect anomaly detection, cause localization, scheduling execution, and model updating into a closed loop, enabling the system to continuously learn and optimize from the execution results, which differs from the open-loop control mode of existing technologies.

[0115] The steps of the various methods described above are only for clarity. In practice, they can be combined into one step or some steps can be split into multiple steps. As long as they include the same logical relationship, they are all within the scope of protection of this patent. Adding insignificant modifications or introducing insignificant designs to the algorithm or process, but without changing the core design of the algorithm and process, are also within the scope of protection of this patent.

[0116] Furthermore, some embodiments of this application also provide an electronic device. The electronic device can be various forms of digital computer, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, etc. The electronic device can also be various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices.

[0117] The electronic device includes: one or more processors; and a memory storing computer program instructions that, when executed, cause the processor to perform the steps of the methods provided in any one or more of the above embodiments. Figure 5 An exemplary structural diagram of the electronic device is disclosed. For example... Figure 5 As shown, the electronic device includes one or more processors 1101, a memory 1102, and interfaces for connecting the components, including high-speed interfaces and low-speed interfaces. The components are interconnected via different buses and can be mounted on a common motherboard or otherwise as required. The processors can process instructions executed within the electronic device, including instructions stored in or on memory to display graphical information of a GUI on an external input / output device (such as a display device coupled to the interface). In some other embodiments, multiple processors and / or multiple buses can be used with multiple memories and multiple memory modules, if desired. Similarly, multiple electronic devices can be connected, each providing some of the necessary operations (e.g., as a server array, a group of blade servers, or a multiprocessor system). The components, their connections and relationships, and their functions shown herein are merely examples and are not intended to limit the implementation of the present application described and / or claimed herein.

[0118] The electronic device may further include an input device 1103 and an output device 1104. The processor 1101, memory 1102, input device 1103, and output device 1104 may be connected via a bus or other means. Figure 5 Taking the example of a connection between China and Israel via a bus.

[0119] Input device 1103 can receive input numerical or character information, and generate key signal inputs related to user settings and function control of the electronic device, such as a touch screen, keypad, mouse, trackpad, touchpad, joystick, one or more mouse buttons, trackball, joystick, etc. Output device 1104 may include a display device, auxiliary lighting device (e.g., LED), and haptic feedback device (e.g., vibration motor). The display device may include, but is not limited to, a liquid crystal display (LCD), a light-emitting diode (LED) display, and a plasma display. In some embodiments, the display device may be a touch screen.

[0120] To provide interaction with the user, the electronic device can be a computer. The computer has: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0121] In this embodiment, a computer-readable storage medium stores a computer program / instructions, which, when executed by a processor, implement the steps of the methods provided in any one or more of the above embodiments. This computer-readable storage medium may be included in the electronic device described in the above embodiments; or it may exist independently and not assembled into that device. The aforementioned computer-readable storage medium carries one or more computer-readable instructions.

[0122] The memory 1102 can serve as a non-transitory computer-readable storage medium, used to store non-transitory software programs, non-transitory computer-executable programs, and modules. The processor 1101 executes various functional applications and data processing of the server by running the non-transitory software programs, instructions, and modules stored in the memory 1102, thereby implementing the program instructions / modules corresponding to the methods provided in any one or more of the embodiments described above in this application.

[0123] The memory 1102 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the electronic device. Furthermore, the memory 1102 may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, the memory 1102 may optionally include memory remotely located relative to the processor 1101, and these remote memories can be connected to the electronic device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0124] It should be noted that the computer-readable storage medium described in this application can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this application, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0125] Computer-readable storage media include permanent and non-permanent, removable and non-removable media, which can store information by any method or technology. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, read-only optical disc (CD-ROM), digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transfer medium that can be used to store information accessible by a computing device.

[0126] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0127] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. For example, it can be implemented using an application-specific integrated circuit (ASIC), a general-purpose computer, or any other similar hardware device. In some embodiments, the software program of this application can be executed by a processor to implement the steps or functions described above. Similarly, the software program of this application (including related data structures) can be stored in a computer-readable recording medium, such as RAM memory, magnetic or optical drives, floppy disks, or similar devices. Furthermore, some steps or functions of this application can be implemented in hardware, for example, as circuitry that works with a processor to perform the various steps or functions.

[0128] The computer program product provided in this application includes one or more computer programs / instructions. When executed by a processor, these computer programs / instructions generate, in whole or in part, the processes or functions described in this application. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium accessible to a computer or a data storage device such as a server or data center that integrates one or more available media. The available medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state disk (SSD)).

[0129] The flowcharts or block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of devices, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-specific system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0130] The scope of this application is defined by the appended claims rather than the foregoing description, and is therefore intended to encompass all variations falling within the meaning and scope of equivalents of the claims. No reference numerals in the claims should be construed as limiting the scope of the claims. Furthermore, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices recited in a device claim may also be implemented by a single unit or device in software or hardware. Terms such as "first," "second," etc., are used only for distinguishing descriptions and do not indicate any particular order, nor should they be construed as indicating or implying relative importance.

[0131] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily made by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims, and the above embodiments should be regarded as exemplary and non-limiting.

Claims

1. A method for coordinated optimization of energy and carbon loads and anomaly attribution, characterized in that, include: Obtain production tasks and energy metering records, and establish a time correlation between the production tasks and the energy metering records, wherein the ratio of the intersection length of the planned execution period and the metering period to the length of the metering period is used as the energy consumption allocation weight. Calculate task-level energy consumption and carbon emissions based on the energy consumption allocation weights; A load baseline is generated based on the current scheduled task load and the measured load of the previous period. The energy and carbon anomaly is calculated based on the load deviation and carbon emission deviation. Identify flexible and rigid loads, and generate multi-objective scheduling optimization strategies based on flexible load capacity and process constraints; Based on the energy and carbon anomaly degree, determine the contribution of the anomaly cause, implement measures, and update the energy consumption baseline.

2. The method as described in claim 1, characterized in that, The process of acquiring production tasks and energy metering records, and establishing a time correlation between the production tasks and the energy metering records, includes: Obtain production tasks containing execution equipment identifiers and planned time windows from the production scheduling system, and obtain metering records containing metering equipment identifiers and sampling time windows from the energy management system; The execution device identifier is matched with the metering device identifier, and the planned time window is intersected with the sampling time window. For production tasks and metering records that simultaneously meet the conditions of device matching and time window intersection, the ratio of the intersection length of the planned time window and the sampling time window to the total length of the sampling time window is calculated and used as the energy consumption allocation weight.

3. The method as described in claim 1, characterized in that, The calculation of task-level energy consumption and carbon emissions based on the energy consumption allocation weight includes: Based on the energy consumption allocation weight, the energy consumption value of each metering record, and the conversion factor corresponding to each energy type, the energy consumption of different metering units is converted to a unified energy caliber, and the task-level standard energy consumption is obtained by summarizing. Based on the energy consumption allocation weight, the energy consumption value of each metering record, and the carbon emission factor corresponding to each energy type in each energy consumption period, the task-level carbon emissions are calculated.

4. The method as described in claim 1, characterized in that, The process of generating a load baseline based on the current scheduled task load and the measured load of the previous time period includes: The standard load of the planned production tasks in the current schedule is summarized by time period. Combined with the measured load of the previous time period, the sum of the measured load and the standard load is weighted and fused according to a preset smoothing coefficient to generate the load baseline.

5. The method as described in claim 1, characterized in that, The calculation of energy carbon anomaly based on load deviation and carbon emission deviation includes: The load deviation is obtained by comparing the measured load during the time period with the load baseline, and the carbon emission deviation is obtained by comparing the total carbon emission value of the task during the time period with the historical carbon emission baseline. The energy-carbon anomaly is obtained by adding the ratio of the absolute value of the load deviation to the sum of the load baseline and the preset constant, and the ratio of the absolute value of the carbon emission deviation to the sum of the historical carbon emission baseline and the preset constant.

6. The method as described in claim 1, characterized in that, The identification of flexible loads and rigid loads includes: Based on process attributes, the scheduling tasks are identified as flexible loads, including drying, heat treatment auxiliary section, air compressor station loading, energy storage charging and discharging, and non-critical test auxiliary loads, while critical processes that affect product quality continuity are identified as rigid loads.

7. The method as described in claim 1, characterized in that, The multi-objective scheduling optimization strategy based on flexible load capacity and process constraints includes: Calculate the adjustable capacity of flexible load for each time period, generate candidate scheduling strategies based on the adjustable capacity of flexible load and process constraints, sum the normalized peak load value, normalized time-of-use energy cost value, normalized time-of-use carbon emission value and normalized delivery deviation value of the candidate scheduling strategies to obtain a score, and select the candidate scheduling strategy with the smallest score as the multi-objective scheduling optimization strategy.

8. An electronic device, characterized in that, The electronic device includes: One or more processors; and A memory storing computer program instructions, which, when executed, cause the processor to perform the steps of the method as described in any one of claims 1 to 7.

9. A computer-readable storage medium having a computer program / instructions stored thereon, characterized in that, When the computer program / instructions are executed by the processor, they implement the steps of the method according to any one of claims 1 to 7.

10. A computer program product comprising a computer program / instructions, characterized in that, When the computer program / instructions are executed by the processor, they implement the steps of the method according to any one of claims 1 to 7.

Images