Energy consumption management and control combined early warning method and platform, medium and computer equipment

Abstract

The invention discloses an energy consumption management and control combined early warning method and platform, a medium and computer equipment. The method comprises the following steps: acquiring energy supply data generated when an energy supply system provides energy for a production workshop; performing standardization processing on the collected energy supply data to obtain standardized energy supply data; in an association rule base, according to the data type of the standardized energy supply data, association rules conforming to the data type are matched; and determining the energy consumption condition of the energy supply system by using the association relationship in the association rule and the standardized energy supply data, positioning abnormal energy consumption according to the energy consumption condition, determining an early warning level, and determining linkage response time efficiency according to the early warning level. According to the invention, full-process management of data linkage analysis, abnormal accurate identification, root automatic positioning and hierarchical linkage response can be realized, and the early warning accuracy of energy consumption and the abnormal processing efficiency are improved.

Description

Technical Field

[0001] This application relates to the field of energy management technology, and in particular to a joint early warning method, platform, medium, and computer equipment for energy consumption control. Background Technology

[0002] With the continuous advancement of the national "dual carbon" goals and the gradual increase in enterprises' demand for refined management, energy management has become a core aspect of cost reduction and efficiency improvement for enterprises. Among them, the energy early warning function is an important component of the energy management system. Summary of the Invention

[0003] In view of this, this application provides a joint early warning method, platform, medium, and computer equipment for energy consumption management, which can realize the whole process management of "data linkage analysis - accurate anomaly identification - automatic root cause location - hierarchical linkage response" and improve the accuracy of energy consumption early warning and the efficiency of anomaly handling.

[0004] According to one aspect of this application, a joint early warning method for energy consumption management is provided, the method comprising: Collect energy supply data generated when the energy supply system provides energy to the production workshop. The types of energy provided by the energy supply system include electricity, natural gas, steam and water resources. The energy supply data includes energy data generated when the energy supply system provides energy, equipment data generated when the energy-consuming equipment in the production workshop is running, production data generated when the production workshop is in production, and environmental data of the environment in which the production workshop is located. The collected energy supply data is standardized to obtain standardized energy supply data; In the association rule base, association rules matching the data type of standardized energy supply data are matched according to the data type. The energy consumption of the energy supply system is determined by using the association relationships in the association rules and the standardized energy supply data. The association rules in the association rule base include basic process rules, equipment characteristic rules, environmental adaptation rules, and safety threshold rules. Basic process rules are used to associate the relationship between production data and energy consumption, as well as the relationship between equipment data and energy consumption. Equipment characteristic rules are used to associate the relationship between equipment data and energy consumption. Environmental adaptation rules are used to associate the relationship between environmental data and energy consumption. Safety threshold rules are used to associate the relationship between equipment data and safety thresholds, as well as the relationship between energy data and safety thresholds. Based on energy consumption data, abnormal energy consumption is identified to determine the early warning level, and the response time is determined according to the early warning level.

[0005] According to another aspect of this application, an energy consumption management and early warning platform is provided, the platform comprising: The data acquisition module is used to collect energy supply data generated when the energy supply system provides energy to the production workshop. The types of energy provided by the energy supply system include electricity, natural gas, steam and water resources. The energy supply data includes energy data generated when the energy supply system provides energy, equipment data generated when the energy-consuming equipment in the production workshop is running, production data generated when the production workshop is in production, and environmental data of the environment in which the production workshop is located. The data preprocessing module is used to standardize the collected energy supply data to obtain standardized energy supply data. The joint analysis module is used to match association rules that conform to the data type of standardized energy supply data in the association rule base. Using the association relationships in the association rules and the standardized energy supply data, the energy consumption of the energy supply system is determined. The association rules in the association rule base include basic process rules, equipment characteristic rules, environmental adaptation rules, and safety threshold rules. Basic process rules are used to associate the relationship between production data and energy consumption, and between equipment data and energy consumption. Equipment characteristic rules are used to associate the relationship between equipment data and energy consumption. Environmental adaptation rules are used to associate the relationship between environmental data and energy consumption. Safety threshold rules are used to associate the relationship between equipment data and safety thresholds, and between energy data and safety thresholds. The early warning decision module is used to locate abnormal energy consumption, determine the early warning level, and determine the linkage response time based on the early warning level. The visualization and interaction module is used to visualize the energy consumption of the identified energy supply system and the energy-consuming equipment with abnormal operating status.

[0006] According to another aspect of this application, a medium is provided having a computer program stored thereon, which, when executed by a processor, implements the above-described joint early warning method for energy consumption control.

[0007] According to another aspect of this application, a computer device is provided, including a medium, a processor, and a computer program stored on the medium and executable on the processor, wherein the processor executes the program to implement the above-described energy consumption control and early warning method.

[0008] By means of the above technical solution, the energy consumption management and control joint early warning method, platform, medium and computer equipment provided in this application can realize the whole process management of "data linkage analysis - accurate identification of anomalies - automatic location of root causes - hierarchical linkage response", and improve the accuracy of energy consumption early warning and the efficiency of anomaly handling.

[0009] The above description is only an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, the following are specific embodiments of this application. Attached Figure Description

[0010] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings: Figure 1 A flowchart illustrating a joint early warning method for energy consumption management provided in an embodiment of this application is shown. Figure 2 A schematic diagram of the architecture of a food processing plant provided in an embodiment of this application is shown; Figure 3 This illustration shows a schematic diagram of a power supply data acquisition process provided in an embodiment of this application; Figure 4 A schematic diagram of the structure of an energy consumption management and early warning platform provided in an embodiment of this application is shown. Detailed Implementation

[0011] The present application will be described in detail below with reference to the accompanying drawings and embodiments. It should be noted that, unless otherwise specified, the embodiments and features described in the embodiments of the present application can be combined with each other.

[0012] This embodiment provides a joint early warning method for energy consumption management, such as... Figure 1 As shown, the method includes: Step 101: Collect energy supply data generated when the energy supply system provides energy to the production workshop. The types of energy provided by the energy supply system include electricity, natural gas, steam and water resources. The energy supply data includes energy data generated when the energy supply system provides energy, equipment data generated when the energy-consuming equipment in the production workshop is running, production data generated when the production workshop is in production, and environmental data of the environment in which the production workshop is located. Step 102: Standardize the collected energy supply data to obtain standardized energy supply data; Step 103: In the association rule base, according to the data type of the standardized energy supply data, match the association rules that conform to the data type, and use the association relationships in the association rules and the standardized energy supply data to determine the energy consumption of the energy supply system. The association rules in the association rule base include basic process rules, equipment characteristic rules, environmental adaptation rules, and safety threshold rules. The basic process rules are used to associate the relationship between production data and energy consumption, and the relationship between equipment data and energy consumption. The equipment characteristic rules are used to associate the relationship between equipment data and energy consumption. The environmental adaptation rules are used to associate the relationship between environmental data and energy consumption. The safety threshold rules are used to associate the relationship between equipment data and safety thresholds, and the relationship between energy data and safety thresholds. Step 104: Based on the energy consumption situation, locate abnormal energy consumption, determine the warning level, and determine the linkage response time based on the warning level.

[0013] Currently, most enterprises' energy management systems adopt a "single-indicator threshold early warning" model. This involves setting fixed thresholds for single energy types such as electricity, natural gas, steam, and water, or for individual equipment such as air compressors, boilers, and refrigeration units. An alarm is triggered when the monitored data exceeds or falls below the threshold. However, the "single-indicator threshold early warning" model has significant drawbacks, specifically: Isolated warning: It fails to take into account the correlation between various energy sources, different types of equipment, and the relationship between energy consumption and the production process. For example, a sudden increase in the power consumption of an air compressor on a certain day may not be due to an abnormality in the power system, but rather to an increase in the energy consumption of the air compressor caused by an increase in the load of equipment in the production workshop. Therefore, a single power warning cannot pinpoint the root cause. False alarm rate: The "single-indicator threshold early warning" model is difficult to adapt to fluctuations in enterprise production. For example, during peak seasons, increased enterprise production capacity is inevitably accompanied by increased energy consumption. If a single fixed threshold is used at this time, false alarms will occur.

[0014] False alarm rate: The "single-indicator threshold early warning" mode may experience "hidden abnormal false alarms." For example, due to equipment efficiency degradation, energy consumption may not reach the threshold but has deviated from the reasonable range, resulting in energy waste. Response lag: It can only "detect anomalies" but cannot automatically link related data to locate the root cause. It requires manual investigation one by one, which prolongs the anomaly handling cycle and exacerbates energy waste.

[0015] Therefore, in the above embodiments of this application, by conducting multi-dimensional data linkage analysis and accurately locating the root cause of anomalies, joint early warning can be achieved, solving the problems of isolated, inefficient, and high false alarm rates of early warning functions in existing energy management systems.

[0016] Specifically, by integrating data on four types of energy resources—electricity, natural gas, steam, and water—along with real-time monitoring of equipment operation, production processes, and environmental parameters, a data system covering the entire energy supply chain has been constructed. Standardized processing eliminates data format differences, providing a unified benchmark for subsequent analysis. The hierarchical design of basic process rules, equipment characteristic rules, and environmental adaptation rules in the association rule base can accurately break down the combined impact of factors such as production capacity, equipment efficiency, and environmental temperature and humidity on energy consumption. For example, equipment characteristic rules can identify power waste caused by a decrease in air compressor gas production efficiency, or environmental adaptation rules can quantify the impact of outdoor temperature fluctuations on the energy consumption of the refrigeration system, enabling rapid identification of the root causes of abnormal energy consumption.

[0017] The safety threshold rules construct a dual protection network by setting safety boundaries for key parameters such as equipment vibration and exhaust pressure, as well as reasonable ranges for energy consumption. When energy consumption data exceeds the threshold, the system automatically matches the warning level (e.g., urgent / emergency / routine) and triggers differentiated response strategies: handling high-risk faults (e.g., equipment overload) within 4 hours, and optimizing inefficient processes (e.g., adjusting production shifts to balance load) within 24 hours. This tiered handling model avoids resource waste and ensures the timely elimination of high-risk hazards, significantly improving the stability and economy of the energy supply system.

[0018] To this end, the entire process from data collection to response execution is automated, reducing errors caused by human intervention. At the same time, the continuously accumulated energy consumption data is used to optimize the association rule base, forming a virtuous cycle of "monitoring-analysis-improvement" to help enterprises achieve green and low-carbon transformation.

[0019] Furthermore, the association rule base, used to store the association logic of "energy-equipment-production-external data" for enterprises (such as food processing plants), may include, for example: Fixed rules (based on human experience and process knowledge), such as a 10% increase in production capacity in a high-temperature workshop leading to a 5%-8% increase in power consumption; when the water pump outlet pressure is maintained at 0.4-0.5MPa, the motor current should be 80-90A; the air compressor exhaust pressure range is 0.6-0.8MPa, corresponding to a current range of 120-150A.

[0020] Dynamic rules (based on algorithms and historical data mining) are used to mine implicit associations in historical data using the Apriori association rule mining algorithm. For example, every 5°C increase in outdoor temperature leads to an 8%-10% increase in chiller energy consumption; every 1°C decrease in chilled water outlet temperature of chiller units leads to a 6%-7% increase in power consumption; every 5°C increase in outdoor temperature leads to a 3% increase in chiller energy consumption; and every 10°C increase in sterilization temperature leads to a 15%-18% increase in natural gas consumption.

[0021] Specifically, when obtaining energy consumption data, it's also possible to pinpoint the root cause of abnormal energy consumption. This pinpointing can be done using an anomaly detection model, which identifies anomalies through both association rule matching and machine learning prediction. Specifically: Next, the real-time collected energy supply data is compared with the aforementioned association rule base.

[0022] Specifically, if the actual energy supply data does not conform to the rules stored in the association rule base, for example, if the production capacity of the high-temperature workshop increases by 5% while the actual power consumption increases by 12%, it will be marked as a "rule-based anomaly".

[0023] Anomaly detection models, such as LSTM (Long Short-Term Memory) neural network models, are trained on historical normal power supply data to predict a reasonable range for real-time power supply data. If the real-time power supply data is higher or lower than the reasonable range threshold predicted by the LSTM model (this threshold is configurable), for example, if energy consumption increases regularly and slowly due to equipment aging, it is marked as a "predictive anomaly".

[0024] When training the LSTM (Long Short-Term Memory) neural network model, the training data can be the target company's normal operation data for the past year (excluding data from equipment failures and shutdowns); the model parameters can be multi-dimensional input features including energy, equipment, production and environment, and the output is the predicted value of each energy consumption. The training iterations are 100 times, and the loss function is controlled to converge to below 0.02.

[0025] The abnormal power supply data marked in the above steps (including data showing regular anomalies and predictive anomalies) are then subjected to reverse correlation tracing to locate the root cause of the anomalies. The steps are as follows: Identify all multi-dimensional data associated with the anomaly. For example, when the power consumption in the high-temperature workshop is abnormal, identify the associated data as air compressor equipment data and high-temperature workshop production capacity data.

[0026] The above-mentioned multi-dimensional real-time power supply data is called up and compared with the historical benchmark data of the past month. The parameters with the highest deviation are selected and combined with the equipment health data to determine the root cause type.

[0027] Optionally, such as Figure 2As shown, for a food processing plant, the production workshop includes a high-temperature workshop, a low-temperature workshop, and a boiler room. The energy-consuming equipment in the production workshop includes a high-temperature cooking oven, a low-temperature sterilizing pot, a boiler, an air compressor, and a refrigeration system. The high-temperature workshop is equipped with a high-temperature cooking oven and an air compressor for the high-temperature workshop. The low-temperature workshop is equipped with a low-temperature sterilizing pot and an air compressor for the low-temperature workshop. The boiler room is equipped with a boiler. The production workshop is laid with a refrigeration system, natural gas pipelines, and steam pipelines, and is equipped with water pumps and a high-voltage distribution cabinet. The refrigeration system includes a refrigeration unit to provide refrigeration to the production workshop. The natural gas pipeline is used to provide natural gas to the production workshop. The steam pipeline is used to provide steam to the production workshop. The water pump is used to provide water to the production workshop. The high-voltage distribution cabinet is used to provide electricity to the production workshop.

[0028] In step 103, the association rule base specifically includes: In the basic process rules, the relationship between production data and energy consumption includes the relationship between production capacity and electricity consumption and steam consumption, respectively. The relationship between equipment data and energy consumption includes the relationship between sterilization process temperature and natural gas consumption. Among them, production data includes production capacity, and equipment data includes the sterilization process temperature of the low-temperature sterilizer. In the equipment characteristic rules, the correlation between equipment data and energy consumption includes the correlation between the air compressor's gas production efficiency and power consumption, the correlation between the boiler's steam output and feedwater hardness and gas consumption, and the correlation between the chilled water temperature of the refrigeration system's chiller and power consumption. Among these, the equipment data includes the air compressor's gas production efficiency, the chilled water temperature of the refrigeration system's chiller, and the boiler's steam output and feedwater hardness. In the environmental adaptation rules, the relationship between environmental data and energy consumption includes the relationship between outdoor temperature and the electricity consumption corresponding to the total energy consumption of the chiller, the relationship between season and gas consumption, and the relationship between outdoor temperature and outdoor humidity and the electricity consumption corresponding to the total energy consumption of the chiller. Among them, the environmental data includes outdoor temperature, season and outdoor humidity. The safety threshold rules define the relationships between equipment data and safety thresholds, including the relationship between the air compressor's discharge pressure and motor current safety thresholds, and the respective safety thresholds for the air compressor's vibration value, the difference between the refrigeration unit's discharge temperature and intake temperature, the boiler's furnace temperature, and the concentration of nitrogen oxides in flue gas. The relationships between energy data and safety thresholds include the relationship between the water pump's outlet pressure and motor current safety thresholds, the safety threshold for the total flow rate of water pumps of the same model operating in parallel, the safety threshold for the voltage of the high-voltage switchgear, the safety threshold for the pressure of the natural gas pipeline, and the safety threshold for the surface temperature of the insulation layer of the steam pipeline. Specifically, equipment data includes the air compressor's discharge pressure, air compressor vibration value, refrigeration unit discharge temperature, boiler furnace temperature, and boiler flue gas nitrogen oxide concentration; energy data includes the water pump's outlet pressure, the total flow rate of water pumps of the same model operating in parallel, the voltage of the high-voltage switchgear, the pressure of the natural gas pipeline, and the surface temperature of the insulation layer of the steam pipeline.

[0029] In the above embodiments of this application, the basic process rules are as shown in Table 1: Table 1

[0030] The equipment characteristic rules are shown in Table 2: Table 2

[0031] The environment adaptation rules are shown in Table 3: Table 3

[0032] Safety threshold rules are shown in Table 4: Table 4

[0033] Optionally, in step 103, the energy consumption of the energy supply system is determined using the association relationships in the association rules and standardized energy supply data, including: Step 1031: For any association rule that matches the data type, substitute the standardized energy supply data into the association relationship in the association rule, and calculate the theoretical consumption value or consumption range of the energy type corresponding to the association rule. Step 1032: For any energy type, sum the consumption calculated by different association rules to obtain the theoretical total consumption value or total consumption range for that energy type. Step 1033: Compare the calculated total consumption theoretical value or total consumption range with the safety threshold of the energy data corresponding to the energy type in the safety threshold rule to verify whether the energy consumption of the energy type is normal, and confirm whether the operating status of the energy-consuming equipment is normal by combining the safety threshold of the equipment data. Step 1034: Combine the verification results and the determination results to output the energy consumption status of the power supply system. The energy consumption status includes the theoretical total consumption value or total consumption range of each energy type, as well as the energy-consuming equipment whose operating status is abnormal.

[0034] In the embodiments described above in this application, in the association rule base, association rules matching the data type of the standardized energy supply data are matched. For example, if the data type involves production capacity and electricity consumption, the association relationship between production capacity and electricity consumption in the basic process rules is selected.

[0035] Substitute standardized energy supply data into the association relationships in successfully matched association rules, and calculate the theoretical consumption value or consumption range of the energy type corresponding to that rule.

[0036] For example, if production capacity increases by 10%, electricity consumption may increase by 5%-8% according to basic process rules. If standardized energy supply data shows that production capacity has indeed increased by 10%, the increase in electricity consumption can be calculated, and thus the theoretical value or range of electricity consumption can be obtained.

[0037] For any energy type, the consumption calculated by different association rules (such as basic process rules, equipment characteristic rules, and environmental adaptation rules) is superimposed.

[0038] For example, regarding electricity consumption, in addition to the increased consumption due to increased production capacity, it is also necessary to consider the impact of equipment characteristics (such as the relationship between the air compressor's gas production efficiency and electricity consumption) and environmental factors (such as the relationship between outdoor temperature and the electricity consumption corresponding to the total energy consumption of the refrigeration unit) on electricity consumption, and to superimpose these consumptions to obtain the total theoretical value or total range of electricity consumption.

[0039] The calculated theoretical value or range of total consumption is compared with the safety threshold of the energy data corresponding to that energy type in the safety threshold rules.

[0040] If the total consumption exceeds the safety threshold, the energy consumption of that energy type is deemed abnormal.

[0041] At the same time, by combining the safety thresholds of the equipment data, it is confirmed whether the operating status of the energy-consuming equipment is normal. For example, check whether the exhaust pressure and vibration value of the air compressor are within the safety thresholds to determine whether the air compressor is operating normally.

[0042] Based on the above verification and determination results, the energy consumption of the power supply system is output.

[0043] Energy consumption data includes the theoretical total consumption or total consumption range for each energy type, as well as energy-consuming equipment operating abnormally. This helps enterprises understand their energy usage in a timely manner, identify abnormal energy consumption and equipment malfunctions, and take corresponding measures for improvement and repair. In short, this method achieves comprehensive monitoring and management of energy consumption in the power supply system through steps such as matching association rules, calculating consumption, superimposing consumption, verifying energy consumption and equipment operating status, and outputting energy consumption data.

[0044] Optionally, in step 101, energy supply data generated when the energy supply system provides energy to the production workshop is collected, including: Step 1011: Collect energy data by deploying smart meters on water pumps, high-voltage distribution cabinets, natural gas pipelines, and steam pipelines respectively; Step 1012: Obtain device data from the corresponding programmable logic controller or data acquisition and monitoring control system of the energy-consuming device through IoT sensors deployed on the energy-consuming device. The IoT sensors include current sensors and pressure sensors. Step 1013: Collect production data through the interface of the manufacturing execution system or enterprise resource planning system connected to the production workshop; Step 1014: Obtain environmental data by deploying temperature and humidity sensors in the production workshop.

[0045] In the above embodiments of this application, energy data may include, for example, electricity (voltage, current, power, total electrical energy, forward active power, reverse active power, maximum demand and occurrence time), natural gas (temperature, pressure, cumulative standard condition flow rate, instantaneous standard condition flow rate), steam (temperature, pressure, cumulative flow rate, instantaneous flow rate), and water resources (pressure, cumulative flow rate, instantaneous flow rate). Equipment data, such as operating parameters (speed, temperature, pressure, current, start-stop status) and health status data (vibration value, insulation resistance) of key energy-consuming equipment (air compressor, boiler, refrigeration unit, water pump, etc.). Production data may include, for example, workshop capacity, production line load, product qualification rate, and process parameters (such as heating temperature, processing time, etc.). Environmental data, such as workshop temperature, humidity, and outdoor weather (temperature, rainfall, etc.).

[0046] To achieve a joint early warning function for the system, multi-dimensional data from the enterprise is collected through IoT sensors, smart meters, and interfaces with PLCs, MES, ERP, and other systems. This data covers energy data, equipment data, production data, and external environmental data. Specifically: (1) For energy data: Smart meters (smart electricity meters, gas meters, etc.) are efficiently networked and their data is converted through devices such as serial port servers and infrared modules. Data is collected, processed at the edge, and transmitted with encryption by deploying different types of gateways in a central and distributed manner.

[0047] (2) For equipment data: acquire data from PLC (Programmable Logic Controller) / SCADA (Supervisory and Data Acquisition System) by deploying IoT sensors (such as current sensors and pressure sensors).

[0048] (3) For production data: Connect to the enterprise MES (Manufacturing Execution System) / ERP (Enterprise Resource Planning) system interface to realize real-time data collection, and the collection frequency is configurable (adjustable from 1 second to 10 minutes).

[0049] (4) For environmental data: external environmental data are obtained by deploying temperature and humidity sensors.

[0050] After edge processing of the collected data, the gateway uploads the data to the EMQX cluster via MQTT and HTTP protocols. The EMQX cluster then performs access authentication, ACL authorization, and rule engine processing on the data uploaded by the enterprise, and finally stores the data in the time series database.

[0051] Specifically, SCADA (Supervisory Control and Data Acquisition) systems are computer-based distributed control systems. They are widely used in power, metallurgy, petroleum, chemical, gas, and railway industries to achieve functions such as data acquisition, equipment control, measurement, parameter adjustment, and various signal alarms. A SCADA system mainly consists of the following components: 1. Lower-level system: also known as remote terminal unit (RTU) or programmable logic controller (PLC), responsible for the acquisition and preliminary processing of field data.

[0052] 2. Host Computer System: Also known as the host unit, it is responsible for receiving data uploaded from the slave devices and performing further processing, analysis, and display. Host computer systems typically have powerful human-machine interfaces (HMIs) that provide monitoring information of on-site production equipment to system operation and management personnel in the form of graphics, images, reports, etc.

[0053] 3. Communication Network System: Responsible for connecting the lower-level and upper-level computers to achieve data transmission and sharing. The communication network system can take various forms such as local area network, wireless network, and Ethernet.

[0054] In joint early warning methods for energy consumption management, SCADA systems play a crucial role. Through smart meters deployed on water pumps, high-voltage switchgear, natural gas pipelines, and steam pipelines, as well as IoT sensors deployed on energy-consuming equipment, SCADA systems can collect real-time energy data, equipment data, production data, and environmental data. After standardization, this data can be matched against rules in a rule-based association database to determine the energy consumption of the power supply system. When the energy consumption meets a preset warning level, an energy consumption warning is sent to a preset receiving terminal.

[0055] Furthermore, for example, energy consumption warnings can be implemented for food processing plants. Energy-consuming equipment includes, for example, two air compressors (one for the high-temperature workshop and one for the low-temperature workshop), one high-temperature cooking oven, one low-temperature sterilizer, two boilers, and one refrigeration system; the main energy sources are electricity, natural gas, and steam.

[0056] Energy data: Install smart meters in the power distribution room (collecting voltage, current, power, and total energy), install smart gas meters in the gas pipeline (collecting temperature, pressure, cumulative standard flow, and instantaneous standard flow), and install steam flow meters in the steam pipeline (collecting temperature, pressure, cumulative flow, and instantaneous flow).

[0057] Equipment data: Vibration sensors and temperature sensors are installed on air compressors, high-temperature cooking ovens, low-temperature sterilizers and boilers to obtain parameters such as current, speed and pressure by connecting to the equipment PLC system; Production data: Access the MES system to obtain the production capacity (tons / hour) of the high-temperature workshop and the low-temperature workshop.

[0058] Environmental data: Temperature and humidity sensors are installed in the workshop and outdoors.

[0059] In one specific embodiment, such as Figure 3 As shown, the energy supply data acquisition follows the logic of "sense layer acquiring raw data - transmission layer preprocessing and networking - processing layer authentication and transfer - storage layer time-series storage". The core components and their functions are as follows: Perception layer: various sensors, smart meters, system interfaces (acquiring raw data); Transport layer: network conversion devices (networking / format conversion), edge gateways (preprocessing / light computing), data collectors (system interface docking); Processing layer: MQTT cluster (identity authentication / ACL authorization / rule engine); Storage layer: TDengine cluster (efficient storage of time-series data).

[0060] Taking a food processing plant (energy-consuming equipment: 2 air compressors, 1 high-temperature cooking oven, 1 low-temperature sterilizer, 2 boilers, 1 refrigeration system; energy types: electricity, natural gas, steam, water resources) as an example, the data collection process is broken down by data type, including, for example: 1. Energy data acquisition (corresponding to step 1011): Data collection targets: "quantity, state, and effect" parameters of electricity, natural gas, steam, and water resources (such as voltage / current of electricity and flow / pressure of natural gas).

[0061] Data collection method: Electricity: Deploy smart meters in the power distribution room to collect data on voltage, current, power, total energy, forward active / reverse active power, maximum demand, and the time of occurrence; Natural gas: Install smart gas meters in gas pipelines to collect temperature, pressure, cumulative standard flow rate, and instantaneous standard flow rate; Steam: Install steam flow meters in the steam pipeline to collect temperature, pressure, cumulative flow, and instantaneous flow. Water resources: Install smart water meters on the water pump outlet pipe to collect pressure, cumulative flow, and instantaneous flow.

[0062] Transmission path: Smart meter — network conversion device (such as serial server, converting RS485 / Modbus signal to Ethernet signal) — edge gateway (preprocessing: filtering noise, format standardization) — MQTT / HTTP protocol — MQTT cluster.

[0063] 2. Equipment data acquisition (corresponding to step 1012): Data collection targets: the "operating status" (e.g., air compressor speed) and "health status" (e.g., air compressor vibration value) of energy-consuming equipment.

[0064] Data collection method: Direct sensor data acquisition: Deploy IoT sensors (vibration sensors—to measure equipment wear, temperature sensors—to measure equipment overheating, current sensors—to measure load rate, and pressure sensors—to measure operating pressure) on air compressors, high-temperature cooking ovens, low-temperature sterilizers, and boilers. System interface integration: The PLC / SCADA system acquires in-depth equipment parameters (such as air compressor speed, sterilization temperature of low-temperature sterilizer, and steam output of boiler) – the PLC acts as the “field data acquisition terminal” and the SCADA system acts as the “equipment monitoring host computer”. The data from both are connected to the transmission layer through network conversion equipment.

[0065] Transmission path: Sensors / PLCs / SCADA—Network conversion devices—Edge gateways / data acquisition units (preprocessing: merging multi-source data and removing duplicate values)—MQTT / HTTP—MQTT cluster.

[0066] 3. Production data collection (corresponding to step 1013): Data collection target: "capacity and load" parameters of the production process (such as the capacity of the high-temperature workshop in "tons / hour").

[0067] Data collection method: Data is collected through the MES / ERP system interface—MES (Manufacturing Execution System) provides real-time production data (such as workshop capacity and production line load), while ERP (Enterprise Resource Planning) supplements it with related data such as production plans and order quantities.

[0068] Transmission path: MES / ERP interface — Data collector (adapting to system protocols such as OPCUA, RESTful) — Network conversion device — MQTT / HTTP — MQTT cluster.

[0069] 4. Environmental data collection (corresponding to step 1014): Data collection target: "Ambient temperature and humidity" in the production environment (such as workshop temperature and outdoor humidity).

[0070] Data collection method: Temperature and humidity sensors are deployed inside the workshop (such as high-temperature / low-temperature workshops) and outdoors to collect environmental parameters in real time.

[0071] Transmission path: Temperature and humidity sensor — edge gateway (preprocessing: filtering data within the effective measurement range) — MQTT / HTTP — MQTT cluster.

[0072] Specifically, the collected raw data needs to undergo preprocessing at the transport layer and authentication at the processing layer before being stored in the time-series database. The process is as follows: 1. Edge gateway preprocessing: "cleaning" the data (e.g., filtering outliers from sensor drift), "standardizing" (e.g., unifying units: converting vibration values ​​from "mV" to "mm / s"), and "lightweighting" (e.g., extracting key fields to reduce transmission volume); 2. MQTT cluster processing: Identity authentication: Verify the legitimacy of devices / sensors (e.g., only authorized smart meters can upload data); ACL authentication: controls data access permissions (e.g., "equipment maintenance personnel" can only view equipment data, while "energy consumption analysts" can view all data); Rule engine: Route data to corresponding business modules (such as "power data" - power consumption analysis, "equipment vibration value" - equipment health warning); 3. TDengine storage: The MQTT cluster writes the processed data into the TDengine cluster (time series database) - TDengine is designed specifically for "time-varying sequence data" (such as voltage values every 10 seconds, gas flow per minute), supports high-concurrency writing and fast querying, and perfectly matches the "time series" characteristics of energy supply data.

[0073] Therefore, through the above process, the data collection of the energy supply system in all dimensions, all links, and the whole life cycle is realized, providing a solid data foundation for subsequent energy consumption correlation analysis (such as the relationship between production capacity and steam consumption) and abnormal warning (such as the vibration value of the air compressor exceeding the standard).

[0074] Optionally, step 104 locates abnormal energy consumption according to the energy consumption situation, determines the warning level, and determines the linkage response time limit according to the warning level, including: Step 1041, determine the warning level according to the determined energy consumption situation and the preset energy consumption level thresholds corresponding to various warning levels, and determine the linkage response time limit according to the warning level. Among them, the linkage response time limit includes an immediate processing time limit, a priority processing time limit, and a secondary priority processing time limit with the processing time increasing in turn.

[0075] In the above embodiments of the present application, hierarchical warning and linkage response can be realized. Among them, for warning classification, according to the abnormal influence range and severity, the warning can be divided into 3 levels: the first level is an emergency warning, which needs to be processed immediately and is triggered when the abnormal energy waste exceeds 10% or the equipment faces a major failure risk; the second level is an important warning, which needs to be processed within 4 hours and is triggered when the abnormal energy waste is between 5% and 10%; the third level is a general warning, which needs to be processed within 24 hours and is triggered when the abnormal energy waste is less than 5%. In each warning level, the percentage of energy waste can be configured.

[0076] Particularly, linkage response can also be realized. The linkage response is divided into automatic response and manual response. Among them, for the automatic response, for equipment that can be remotely controlled, an adjustment instruction is automatically generated and sent to the PLC system for execution. For the manual response, notifications are pushed to the corresponding personnel according to different warning levels. Among them, for the first-level warning, text messages and WeChat are pushed and audible and visual alarms are given; for the second-level warning, WeChat and emails are pushed; for the third-level warning, emails are pushed. The push content includes the abnormal details and the reasons for the abnormality.

[0077] Optionally, the method further includes: Step 105, visually display the determined energy consumption situation of the energy supply system and the energy-consuming equipment with abnormal operating status.

[0078] In the embodiments described above, early warning information can be presented visually, supporting user operation and tracking. The main display interface may include: an anomaly monitoring dashboard, an anomaly history log, and an anomaly handling log. The anomaly monitoring dashboard displays the real-time operating status (normal / abnormal) and early warning information of various types of energy and equipment. Early warning levels are distinguished by color: red represents a level one warning, yellow represents a level two warning, and blue represents a level three warning. The anomaly history log records the associated equipment and production data based on different anomaly types and labels the cause of the anomaly. For example, in the power anomaly type, it records an anomaly in air compressor #1, where the current is 15% higher than the baseline, but the high-temperature workshop's production capacity is normal; the cause of the anomaly is bearing wear. The anomaly handling log records the early warning trigger time, personnel involved, handling measures, and handling results, forming a closed-loop management system.

[0079] Optionally, step 102 standardizes the collected energy supply data to obtain standardized energy supply data, including: Step 1021: For any type of energy supply data, the Laida criterion is used to calculate the standard deviation of the energy supply data, and energy supply data that exceed a preset multiple of the standard deviation are identified as outliers and removed. Step 1022: For the energy supply data after removing outliers, the moving average method is used to fill in the missing values, and the energy supply data of different units and magnitudes are unified into standard unit data to obtain standardized energy supply data.

[0080] In the above embodiments of this application, the collected raw data can be cleaned and standardized to eliminate data noise and format differences, providing high-quality data for subsequent joint analysis, specifically including: (1) Data cleaning: The "Raida criterion" can be used to determine the confidence interval by calculating the standard deviation. Data exceeding 3 times the standard deviation (|x-μ|>3σ) are identified as outliers and removed (e.g., jump data caused by smart meter failure); The "moving average method" can be used to calculate the moving average by sequentially adding and subtracting new and old data to fill in missing values ​​(e.g., missing data collected in a short period of time due to communication network interruption).

[0081] (2) Data standardization: unify data of different units and magnitudes into “standard unit data” (for example, steam meters unify pressure units Pa and kPa into Pa).

[0082] By applying the technical solution of this embodiment, multi-dimensional data-driven joint early warning replaces traditional single-indicator threshold early warning. Utilizing a relational rule base matching mechanism and machine learning detection mechanism, the false alarm rate can be reduced while avoiding missed alarms, demonstrating high recognition accuracy for hidden anomalies such as equipment aging. Automatic correlation and tracing of anomaly root causes eliminates the need for manual investigation, reducing anomaly location time and improving processing efficiency. Through a linkage response mechanism, automatic equipment adjustment and hierarchical anomaly management are achieved, forming a closed loop from discovery to handling, reducing the company's average monthly energy waste. The correlation rule base can be dynamically adjusted according to changes in enterprise processes and equipment updates, adapting to the energy management needs of different industries such as manufacturing, chemical, metallurgy, and food processing.

[0083] Furthermore, as Figure 1 In terms of specific implementation, this application provides an energy consumption management and early warning platform, such as... Figure 4 As shown, the platform includes: The data acquisition module 201 is used to collect energy supply data generated when the energy supply system provides energy to the production workshop. The types of energy provided by the energy supply system include electricity, natural gas, steam and water resources. The energy supply data includes energy data generated when the energy supply system provides energy, equipment data generated when the energy-consuming equipment in the production workshop is running, production data generated when the production workshop is in production, and environmental data of the environment in which the production workshop is located. The data preprocessing module 202 is used to standardize the collected energy supply data to obtain standardized energy supply data. The joint analysis module 203 is used to match association rules that conform to the data type of standardized energy supply data in the association rule base, and use the association relationships in the association rules and the standardized energy supply data to determine the energy consumption of the energy supply system. The association rules in the association rule base include basic process rules, equipment characteristic rules, environmental adaptation rules and safety threshold rules. The basic process rules are used to associate the relationship between production data and energy consumption, and the relationship between equipment data and energy consumption. The equipment characteristic rules are used to associate the relationship between equipment data and energy consumption. The environmental adaptation rules are used to associate the relationship between environmental data and energy consumption. The safety threshold rules are used to associate the relationship between equipment data and safety thresholds, and the relationship between energy data and safety thresholds. The early warning decision module 204 is used to locate abnormal energy consumption, determine the early warning level, and determine the linkage response time based on the early warning level; The visualization interaction module 205 is used to visualize the energy consumption of the determined energy supply system and the energy-consuming equipment with abnormal operating status.

[0084] In the above embodiments of this application, for example, at 10:00 on September 3, 2025, the data acquisition module 201 obtained that the power consumption of the high-temperature workshop was 2050 kWh / hour, which is 20.6% higher than the same period of the previous day (1700 kWh / hour); at the same time, the high-temperature workshop capacity during this period was obtained from the MES system as 12 tons, which is 9.1% higher than the same period of the previous day (115 tons).

[0085] The data preprocessing module 202 performs data cleaning to ensure there are no outliers or missing values, and performs data standardization to obtain a power consumption of 2050 kWh / hour and a production capacity of 120 tons.

[0086] The joint analysis module 203 is used for fixed rule matching. For example, if the high-temperature workshop's capacity increases by 9.1%, according to the fixed rule "capacity increase of 10% - electricity increase of 5%-8%", the reasonable electricity increase should be ≤7.3%. The actual increase is 20.6%, which is marked as a "rule-based anomaly". Machine learning detection, based on the LSTM long short-term memory neural network model, predicts that the reasonable range for electricity consumption in the high-temperature workshop during this period is 1780-1850 kWh / hour. 2050 kWh exceeds the upper limit of the range by 10.8%, which is marked as a "predictive anomaly". Root cause identification involves correlating the data of air compressor #1 (current 165A, exceeding the rule threshold of 150A) and vibration value (0.8 mm / s, exceeding the normal range of 0.3-0.5 mm / s), and comparing it with historical benchmark data (current of 130-140A in the same period of the past 7 days). The root cause is identified as wear of the bearing of air compressor #1, which leads to increased current and causes abnormal electricity consumption.

[0087] The early warning decision module 204 is used for early warning classification. If the power consumption exceeds the upper limit by more than 10% and the air compressor faces the risk of failure, it is judged as a level one early warning (red). It also performs linkage response, including automatic response, which generates an instruction to "reduce the exhaust pressure of air compressor 1# to 0.7MPa" and sends it to the PLC system to reduce the current to 135A; manual response, which sends a text message and WeChat push to the enterprise equipment administrator, with the content "wearing of bearing 1# of air compressor in high temperature workshop has caused abnormal power increase of 10.8%, and it is recommended to stop the machine for maintenance immediately", and triggers the audible and visual alarm of high temperature workshop.

[0088] The visualization and interaction module 205 processes and tracks records, such as: at 10:30 on September 3, 2025, the equipment administrator shut down the machine for maintenance, confirmed that the No. 1 bearing of the air compressor was worn, and replaced the bearing; at 11:00 on September 3, 2025, the air compressor restarted, the current recovered to 135A, and the power consumption dropped to 1800kWh / hour, returning to a reasonable range; at the same time, the anomaly handling log records the entire process from the triggering of the warning to the final recovery of the equipment on site, and forms a "Level 1 Warning Handling Report".

[0089] It should be noted that other corresponding descriptions of the functional units involved in the energy consumption management and early warning platform provided in this application embodiment can be found by referring to... Figures 1 to 3 The corresponding descriptions in the method will not be repeated here.

[0090] Based on the above, Figures 1 to 3 Accordingly, this application also provides a medium on which a computer program is stored, which, when executed by a processor, implements the above-described method. Figures 1 to 3 The energy consumption control and joint early warning method is shown.

[0091] Based on this understanding, the technical solution of this application can be embodied in the form of a software product, which can be stored in a non-volatile medium (such as CD-ROM, USB flash drive, mobile hard drive, etc.) and includes several instructions to cause a computer device (such as personal computer, server, or network device, etc.) to execute the methods described in the various implementation scenarios of this application.

[0092] Based on the above, Figures 1 to 3 The method shown, and Figure 4 To achieve the above objectives, the virtual platform embodiment shown in this application also provides a computer device, specifically a personal computer, server, network device, etc. This computer device includes a medium and a processor; the medium is used to store a computer program; the processor is used to execute the computer program to achieve the above-described objectives. Figures 1 to 3 The energy consumption control and joint early warning method is shown.

[0093] Optionally, the computer device may also include a user interface, a network interface, a camera, radio frequency (RF) circuitry, sensors, audio circuitry, a Wi-Fi module, etc. The user interface may include a display screen, input units such as a keyboard, etc., and optional user interfaces may also include USB ports, card reader ports, etc. The network interface may optionally include standard wired interfaces, wireless interfaces (such as Bluetooth interfaces, Wi-Fi interfaces), etc.

[0094] Those skilled in the art will understand that the computer device structure provided in this embodiment does not constitute a limitation on the computer device, and may include more or fewer components, or combine certain components, or have different component arrangements.

[0095] The medium may also include an operating system and a network communication module. The operating system is a program that manages and stores the hardware and software resources of a computer device, supporting the operation of information processing programs and other software and / or programs. The network communication module is used to enable communication between the various components within the medium, as well as communication with other hardware and software within the physical device.

[0096] Through the above description of the implementation methods, those skilled in the art can clearly understand that this application can be implemented using software plus necessary general-purpose hardware platforms, or it can be implemented using hardware to collect energy supply data generated when the energy supply system provides energy to the production workshop; the collected energy supply data is standardized to obtain standardized energy supply data; in the association rule base, according to the data type of the standardized energy supply data, association rules matching the data type are matched; using the association relationships in the association rules and the standardized energy supply data, the energy consumption of the energy supply system is determined; based on the energy consumption, abnormal energy consumption is located, the warning level is determined, and the linkage response time is determined based on the warning level. This enables full-process management of "data linkage analysis - accurate anomaly identification - automatic root cause location - hierarchical linkage response," improving the accuracy of energy consumption warnings and the efficiency of anomaly handling.

[0097] Those skilled in the art will understand that the accompanying drawings are merely schematic diagrams of a preferred embodiment, and the modules or processes shown in the drawings are not necessarily essential for implementing this application. Those skilled in the art will understand that the modules in the platform within the embodiment can be distributed within the platform as described in the embodiment, or they can be modified to reside in one or more platforms different from this embodiment. The modules in the above-described embodiment can be merged into one module, or further divided into multiple sub-modules.

[0098] The serial numbers in this application are for descriptive purposes only and do not represent the superiority or inferiority of any particular implementation scenario. The above disclosures are merely a few specific implementation scenarios of this application; however, this application is not limited thereto, and any modifications that can be made by those skilled in the art should fall within the protection scope of this application.

Claims

1. A joint early warning method for energy consumption management, characterized in that, The method includes: Collect energy supply data generated when the energy supply system provides energy to the production workshop. The types of energy provided by the energy supply system include electricity, natural gas, steam and water resources. The energy supply data includes energy data generated when the energy supply system provides energy, equipment data generated when the energy-consuming equipment in the production workshop is running, production data generated when the production workshop is in production, and environmental data of the environment in which the production workshop is located. The collected energy supply data is standardized to obtain standardized energy supply data; In the association rule base, association rules matching the data type of standardized energy supply data are matched according to the data type. The energy consumption of the energy supply system is determined by using the association relationships in the association rules and the standardized energy supply data. The association rules in the association rule base include basic process rules, equipment characteristic rules, environmental adaptation rules, and safety threshold rules. Basic process rules are used to associate the relationship between production data and energy consumption, as well as the relationship between equipment data and energy consumption. Equipment characteristic rules are used to associate the relationship between equipment data and energy consumption. Environmental adaptation rules are used to associate the relationship between environmental data and energy consumption. Safety threshold rules are used to associate the relationship between equipment data and safety thresholds, as well as the relationship between energy data and safety thresholds. Based on energy consumption data, abnormal energy consumption is identified to determine the early warning level, and the response time is determined according to the early warning level.

2. The method according to claim 1, characterized in that, The production workshop includes a high-temperature workshop, a low-temperature workshop, and a boiler room. The energy-consuming equipment in the production workshop includes a high-temperature cooking oven, a low-temperature sterilizing pot, a boiler, an air compressor, and a refrigeration system. The high-temperature workshop is equipped with a high-temperature cooking oven and an air compressor specifically for high-temperature workshops. The low-temperature workshop is equipped with a low-temperature sterilizing pot and an air compressor specifically for low-temperature workshops. The boiler room is equipped with a boiler. The production workshop is laid with a refrigeration system, natural gas pipelines, and steam pipelines, and is equipped with water pumps and a high-voltage distribution cabinet. The refrigeration system includes a refrigeration unit to provide refrigeration to the production workshop. The natural gas pipeline is used to provide natural gas to the production workshop. The steam pipeline is used to provide steam to the production workshop. The water pump is used to provide water to the production workshop. The high-voltage distribution cabinet is used to provide electricity to the production workshop. In the basic process rules, the relationship between production data and energy consumption includes the relationship between production capacity and electricity consumption and steam consumption, respectively. The relationship between equipment data and energy consumption includes the relationship between sterilization process temperature and natural gas consumption. Among them, production data includes production capacity, and equipment data includes the sterilization process temperature of the low-temperature sterilizer. In the equipment characteristic rules, the correlation between equipment data and energy consumption includes the correlation between the air compressor's gas production efficiency and power consumption, the correlation between the boiler's steam output and feedwater hardness and gas consumption, and the correlation between the chilled water temperature of the refrigeration system's chiller and power consumption. Among these, the equipment data includes the air compressor's gas production efficiency, the chilled water temperature of the refrigeration system's chiller, and the boiler's steam output and feedwater hardness. In the environmental adaptation rules, the relationship between environmental data and energy consumption includes the relationship between outdoor temperature and the electricity consumption corresponding to the total energy consumption of the chiller, the relationship between season and gas consumption, and the relationship between outdoor temperature and outdoor humidity and the electricity consumption corresponding to the total energy consumption of the chiller. Among them, the environmental data includes outdoor temperature, season and outdoor humidity. The safety threshold rules define the relationships between equipment data and safety thresholds, including the relationship between the safety thresholds of air compressor discharge pressure and motor current, and the respective safety thresholds for air compressor vibration, the difference between refrigeration unit discharge temperature and intake temperature, boiler furnace temperature, and flue gas nitrogen oxide concentration. The relationships between energy data and safety thresholds include the relationship between water pump outlet pressure and motor current, the safety threshold for the total flow rate of water pumps of the same model operating in parallel, the safety threshold for voltage of high-voltage switchgear, the safety threshold for pressure of natural gas pipelines, and the safety threshold for surface temperature of insulation layer of steam pipelines. Specifically, equipment data includes air compressor discharge pressure, air compressor vibration, refrigeration unit discharge temperature, boiler furnace temperature, and boiler flue gas nitrogen oxide concentration; energy data includes water pump outlet pressure, total flow rate of water pumps of the same model operating in parallel, voltage of high-voltage switchgear, pressure of natural gas pipelines, and surface temperature of insulation layer of steam pipelines.

3. The method according to claim 2, characterized in that, The process of determining the energy consumption of the energy supply system using association rules and standardized energy supply data includes: For any association rule that matches the data type, the standardized energy supply data is substituted into the association relationship in the association rule, and the theoretical consumption value or consumption range of the energy type corresponding to the association rule is calculated. For any energy type, the consumption calculated by different association rules is summed to obtain the theoretical total consumption value or total consumption range for that energy type: The calculated total consumption theoretical value or total consumption range is compared with the safety threshold of the energy data corresponding to the energy type in the safety threshold rule to verify whether the energy consumption of the energy type is normal, and combined with the safety threshold of the equipment data, to confirm whether the operating status of the energy-consuming equipment is normal. The energy consumption status of the power supply system is output by combining the verification results and the determination results. The energy consumption status includes the theoretical value or range of total consumption for each energy type, as well as the energy-consuming equipment that is in an abnormal operating state.

4. The method according to claim 3, characterized in that, The method further includes: The energy consumption of the power supply system is visualized, as well as the energy-consuming equipment that is not operating normally.

5. The method according to claim 2, characterized in that, The energy supply data generated when the energy collection and supply system provides energy to the production workshop includes: Energy data is collected by smart meters deployed on water pumps, high-voltage switchgear, natural gas pipelines, and steam pipelines. By deploying IoT sensors on energy-consuming devices, device data on the corresponding programmable logic controller or data acquisition and monitoring control system of the energy-consuming device can be obtained. Among them, IoT sensors include current sensors and pressure sensors. Production data is collected through the interfaces of the manufacturing execution system or enterprise resource planning system connected to the production workshop; Environmental data is acquired by deploying temperature and humidity sensors in the production workshop.

6. The method according to claim 1, characterized in that, Based on energy consumption patterns, abnormal energy consumption is identified to determine the warning level, and the response time is determined according to the warning level, including: Based on the determined energy consumption situation and the preset energy consumption thresholds corresponding to various warning levels, the warning level is determined, and the linkage response time is determined according to the warning level. The linkage response time includes the immediate processing time, the priority processing time, and the second priority processing time, which are progressively larger in terms of processing time.

7. The method according to any one of claims 1 to 6, characterized in that, The standardization process for the collected energy supply data to obtain standardized energy supply data includes: For any type of energy supply data, the Laida criterion is used to calculate the standard deviation of the energy supply data, and energy supply data that exceed a preset multiple of the standard deviation are identified as outliers and removed. After removing outliers, the missing values ​​in the energy supply data are filled in using the moving average method. Then, the energy supply data of different units and magnitudes are unified into standard unit data to obtain standardized energy supply data.

8. A joint early warning platform for energy consumption management, characterized in that, The platform includes: The data acquisition module is used to collect energy supply data generated when the energy supply system provides energy to the production workshop. The types of energy provided by the energy supply system include electricity, natural gas, steam and water resources. The energy supply data includes energy data generated when the energy supply system provides energy, equipment data generated when the energy-consuming equipment in the production workshop is running, production data generated when the production workshop is in production, and environmental data of the environment in which the production workshop is located. The data preprocessing module is used to standardize the collected energy supply data to obtain standardized energy supply data. The joint analysis module is used to match association rules that conform to the data type of standardized energy supply data in the association rule base. Using the association relationships in the association rules and the standardized energy supply data, the energy consumption of the energy supply system is determined. The association rules in the association rule base include basic process rules, equipment characteristic rules, environmental adaptation rules, and safety threshold rules. Basic process rules are used to associate the relationship between production data and energy consumption, and between equipment data and energy consumption. Equipment characteristic rules are used to associate the relationship between equipment data and energy consumption. Environmental adaptation rules are used to associate the relationship between environmental data and energy consumption. Safety threshold rules are used to associate the relationship between equipment data and safety thresholds, and between energy data and safety thresholds. The early warning decision module is used to locate abnormal energy consumption, determine the early warning level, and determine the linkage response time based on the early warning level. The visualization and interaction module is used to visualize the energy consumption of the identified energy supply system and the energy-consuming equipment with abnormal operating status.

9. A medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the energy consumption control and joint early warning method according to any one of claims 1 to 7.

10. A computer device, comprising a medium, a processor, and a computer program stored on the medium and executable on the processor, characterized in that, When the processor executes the computer program, it implements the energy consumption control and joint early warning method according to any one of claims 1 to 7.

Images