Industrial production monitoring method and monitoring device applied to pollution reduction and carbon reduction of ecological environment

Abstract

The embodiment of the invention discloses an industrial production monitoring method and monitoring device applied to pollution reduction and carbon reduction of an ecological environment. The method comprises the following steps: firstly, obtaining an operation parameter of target industrial production equipment and an environment parameter set of an associated region; secondly, processing the operation parameters and the environment parameter set through a pre-trained pollution and carbon reduction prediction model, and outputting a pollution emission feature vector and a dynamic emission reduction strategy of the target industrial production equipment; then generating a multi-level control instruction set (an equipment operation parameter adjustment threshold, an energy switching priority and a pollution processing node start-stop rule) for the target industrial production equipment according to the pollution emission feature vector and a dynamic emission reduction strategy; and finally, the multi-level control instruction set is transmitted to a control terminal of the target industrial production equipment through an Internet of Things interface, and the execution weight of the multi-level control instruction set is dynamically adjusted based on the environment parameter updating set fed back in real time. In this way, pollution reduction and carbon reduction of industrial production can be achieved in a high-quality and intelligent mode.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of data analysis technology, and specifically to an industrial production monitoring method and a monitoring device applied to ecological environment pollution reduction and carbon reduction. Background Art

[0002] In recent years, in order to avoid further deterioration of the ecological environment, pollution control and carbon emission reduction technologies in industrial production processes are crucial.

[0003] However, existing pollution control and carbon reduction technologies have certain defects. For example, traditional methods mostly use a single-dimensional monitoring and control mechanism, and usually collect emission parameters in a discrete manner based on fixed thresholds, lacking dynamic coupling analysis of equipment operating conditions and environmental factors. Some improvement plans attempt to introduce machine learning algorithms for emission prediction, but their model training data does not cover the operating status of the equipment throughout its life cycle, resulting in significant deviations in the prediction results when the operating conditions suddenly change.

[0004] In addition, existing pollution treatment control technologies usually adopt a switch-type start-stop mechanism, lacking a collaborative computing mechanism, which can easily lead to a surge in energy consumption caused by frequent start-stops of processing units. At the same time, this type of pollution treatment control technology is difficult to achieve real-time optimization and iteration of control strategies. It can be seen that how to achieve high-quality and intelligent pollution reduction and carbon reduction in industrial production is a technical problem that urgently needs to be overcome. Summary of the invention

[0005] The embodiments of the present invention provide an industrial production monitoring method and a monitoring device for ecological environmental pollution reduction and carbon reduction, which are used to achieve high-quality and intelligent pollution reduction and carbon reduction in industrial production.

[0006] In the first aspect, an embodiment of the present invention provides an industrial production monitoring method applied to ecological environment pollution reduction and carbon reduction, which is applied to an industrial production monitoring device, and the method includes: obtaining operating parameters of target industrial production equipment and a set of environmental parameters of an associated area, the set of environmental parameters including atmospheric pollutant concentration, carbon emission intensity and energy consumption rate; processing the operating parameters and the set of environmental parameters through a pre-trained pollution reduction and carbon reduction prediction model, and outputting a pollution emission characteristic vector and a dynamic emission reduction strategy for the target industrial production equipment; generating a multi-level control instruction set for the target industrial production equipment according to the pollution emission characteristic vector and the dynamic emission reduction strategy, the multi-level control instruction set including equipment operating parameter adjustment thresholds, energy switching priorities and pollution treatment node start and stop rules; transmitting the multi-level control instruction set to the control terminal of the target industrial production equipment through an Internet of Things interface, and dynamically adjusting the execution weight of the multi-level control instruction set based on the real-time feedback environmental parameter update set.

[0007] In a second aspect, an embodiment of the present invention provides an industrial production monitoring device, including: processor; a storage device having a computer program stored thereon, When the computer program is executed by the processor, the processor implements any of the industrial production monitoring methods applied to ecological environment pollution reduction and carbon reduction.

[0008] An embodiment of the present invention provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, the steps of the industrial production monitoring method applied to ecological environment pollution reduction and carbon reduction are implemented.

[0009] It can be seen that the embodiment of the present invention has the following beneficial effects: first, the operating parameters of the target industrial production equipment and the environmental parameter set of the associated area are obtained; secondly, the operating parameters and the environmental parameter set are processed through the pre-trained pollution reduction and carbon reduction prediction model, and the pollution emission characteristic vector and dynamic emission reduction strategy of the target industrial production equipment are output; then, according to the pollution emission characteristic vector and the dynamic emission reduction strategy, a multi-level control instruction set (equipment operating parameter adjustment threshold, energy switching priority and pollution treatment node start and stop rules) for the target industrial production equipment is generated; finally, the multi-level control instruction set is transmitted to the control terminal of the target industrial production equipment through the Internet of Things interface, and the execution weight of the multi-level control instruction set is dynamically adjusted based on the real-time feedback environmental parameter update set. With such a design, pollution reduction and carbon reduction in industrial production can be achieved in a high-quality and intelligent manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 A flow chart of an industrial production monitoring method for reducing pollution and carbon emissions in the ecological environment provided by an embodiment of the present invention.

[0011] Figure 2 A schematic diagram of the basic structure of an industrial production monitoring device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0012] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the embodiments of the present invention are further described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0013] See also Figure 1 As shown in FIG. 1 , this figure is a flow chart of an industrial production monitoring method for reducing pollution and carbon emissions in the ecological environment provided by an embodiment of the present invention. The method can be applied to an industrial production monitoring device. Figure 1 As shown, the method may include S102-S108.

[0014] S102: Acquire operating parameters of target industrial production equipment and a set of environmental parameters of associated areas, where the set of environmental parameters includes atmospheric pollutant concentration, carbon emission intensity, and energy consumption rate.

[0015] In S102, the industrial production monitoring device collects the operating parameters of the target industrial production equipment and the environmental parameter set of the associated area in real time through a multi-dimensional sensor network deployed in the coke oven body (target industrial production equipment) and the periphery of the plant (associated area) of the coke plant. Specifically, the operating parameters of the coke oven body include key operating indicators such as the temperature gradient distribution inside the coke drum, the travel speed of the coke pusher, and the opening of the gas injection valve. These parameters are obtained through measuring elements such as embedded thermocouple arrays, laser displacement sensors, and pressure transmitters at a sampling frequency of several times per second.

[0016] The environmental parameter set of the associated area is continuously obtained by environmental monitoring stations distributed within a radius of several hundred meters in the coking plant area. The concentration of atmospheric pollutants is measured by a β-ray absorption particle monitor and an ultraviolet differential absorption spectrometer to simultaneously measure the real-time concentrations of PM2.5, benzopyrene and hydrogen sulfide; the carbon emission intensity is measured by tunable diode laser absorption spectroscopy technology to measure the CO in the exhaust gas flow of the coke oven chimney. 2 , CH 4 The concentration is analyzed online; the energy consumption rate is recorded by the smart meter group and the steam flow meter respectively to record the power load curve of the coke oven heating system and the steam output rate of the waste heat boiler. The above parameter data is encapsulated by the industrial bus protocol to form a multi-modal data stream with timestamp alignment and transmitted to the edge computing unit of the industrial production monitoring device.

[0017] S104: Processing the operating parameters and the environmental parameter set through a pre-trained pollution reduction and carbon reduction prediction model, and outputting the pollution emission characteristic vector and dynamic emission reduction strategy of the target industrial production equipment.

[0018] In S104, the industrial production monitoring device calls the pollution reduction and carbon reduction prediction model deployed in the GPU acceleration module to perform coupling analysis on the coke oven operating parameters and regional environmental parameters. The pollution reduction and carbon reduction prediction model is based on a deep temporal convolutional network architecture and is pre-trained through several sets of operating condition-environment mapping data accumulated during the historical production cycle. Its hidden layer contains more than 10 dilated causal convolution modules, which can extract the nonlinear correlation characteristics between the coke oven combustion efficiency and the diffusion of pollutants.

[0019] When the real-time collected coke pushing cycle parameters and PM2.5 exceeding standard data on the southwest side of the plant are input, the pollution reduction and carbon reduction prediction model first performs a partial correlation analysis on the fluctuation of coal gas calorific value and the benzopyrene generation rate, and then locates the core variable group that affects the carbon emission peak through the attention mechanism, and finally outputs a pollution emission feature vector containing multi-dimensional features. For example, the third-dimensional eigenvalue reflects the dynamic correlation coefficient between the reversing cycle of the coke oven regenerator and the NOx emission, and the seventh-dimensional eigenvalue represents the quantitative relationship between the coke maturity and the volatile organic compound escape rate. Based on the pollution emission feature vector, the pollution reduction and carbon reduction prediction model simultaneously generates a dynamic emission reduction strategy set, which includes the air-fuel ratio optimization scheme of the coke oven combustion chamber, the pressure adjustment gradient of the raw gas purification system, and the coordinated operation schedule of the dry coke quenching device and the wet desulfurization tower. Each strategy item is accompanied by a confidence score and a response priority parameter.

[0020] S106: Generate a multi-level control instruction set for the target industrial production equipment according to the pollution emission characteristic vector and the dynamic emission reduction strategy, wherein the multi-level control instruction set includes equipment operation parameter adjustment thresholds, energy switching priorities, and pollution treatment node start and stop rules.

[0021] In S106, the industrial production monitoring device constructs a multi-level control command system for the coking production line based on the modal decomposition results of the pollution emission characteristic vector. For example, for the coke oven body preparation layer, based on the VOCs control threshold corresponding to the seventh-dimensional eigenvalue, a coke pusher positioning accuracy compensation command is generated, requiring that when the center temperature of the coke cake reaches 1050±15℃, the riser water seal height adjustment mechanism is automatically triggered.

[0022] At the energy supply level, based on the forecast of carbon emission intensity trends, a priority matrix for switching between coal gas and natural gas dual fuels is formulated, stipulating that when the environmental monitoring station detects that the benzopyrene concentration in the downwind direction exceeds 2.5ng / m³, the coke oven gas main pipeline shut-off device is immediately activated and gradually replaced with high calorific value natural gas at a ratio of 1:0.7.

[0023] In the pollution treatment layer, combined with the equipment response delay parameters in the dynamic emission reduction strategy, the start-stop rules of the chemical product recovery section are generated, and it is clear that the crude benzene scrubber should start the emergency absorption mode 10 seconds in advance when the pressure fluctuation of the coke oven gas collecting pipe exceeds 150Pa, and the desulfurization regeneration tower needs to start the emergency absorption mode according to the tail gas H 2 The S concentration gradient changes to implement variable period regeneration operation.

[0024] All the above control instructions can be verified for their logical completeness through Petri net modeling, and a mapping relationship with the interlocking protection mechanism of the DCS system can be established.

[0025] S108: Transmitting the multi-level control instruction set to the control terminal of the target industrial production equipment through the Internet of Things interface, and dynamically adjusting the execution weight of the multi-level control instruction set based on the real-time feedback environmental parameter update set.

[0026] In S108, the industrial production monitoring device transmits the multi-level control instruction set to the distributed control system of the coking plant central control room through the OPC UA protocol, and at the same time establishes a two-way data channel with the coke oven temperature probe and the dust removal fan inverter.

[0027] For example, when executing the instruction to improve the sealing of the coke side furnace door, the industrial production monitoring device continuously receives real-time temperature field distribution data uploaded by dozens of infrared thermal imagers installed on the top of the coke oven. If an abnormal temperature rise area of ​​more than 50°C is detected in the southeast corner of carbonization chamber No. 3, the execution weight of the equipment sealing strip clamping force adjustment instruction is immediately increased from 0.7 to 0.9 based on the benzopyrene concentration growth rate in the updated environmental parameter set, and the priority of the coke pushing car travel speed control item is reduced.

[0028] For another example, for the command adjustment of the gas purification system, the industrial production monitoring device obtains the secondary voltage fluctuation data of the electric tar collector through the Modbus / TCP interface every 200 milliseconds. When it is found that the deviation from the preset capture efficiency curve exceeds 12%, the online correction module of the dynamic emission reduction strategy is automatically triggered, the start and stop frequency of the washing liquid circulation pump is recalculated, and the updated control parameters are sent to the on-site actuator through the industrial wireless Mesh network. The entire process complies with the safety integrity level requirements of the IEC 61508 standard to ensure that the transmission delay of the control command is always less than tens of milliseconds.

[0029] In detail, in the above technical solution, the threshold value for adjusting the equipment operating parameters refers to the critical value or interval range of key parameters set by industrial production equipment during dynamic regulation according to real-time working conditions and environmental feedback, which is used as the benchmark condition for triggering or terminating specific control actions. In complex industrial scenarios such as the coke oven body of a coking plant, the threshold value for adjusting the equipment operating parameters can be obtained through the coupling analysis of multi-dimensional sensor data and prediction models, aiming to balance production efficiency and environmental protection goals.

[0030] For example, in the optimization scheme of the air-fuel ratio of the coke oven combustion chamber, the adjustment thresholds may include the upper and lower limits of the temperature gradient distribution inside the coke tower (such as 1050±15℃), the safe range of the gas injection valve opening (such as 30%-70%), and the fluctuation tolerance of the coke pusher's travel speed (such as ±0.2m / s). The setting of these thresholds is based on the correlation analysis of historical production data and the law of pollutant generation. For example, when the coke cake is not mature enough, premature coke pushing will cause the volatile organic compounds (VOCs) to exceed the escape rate. Therefore, it is necessary to monitor the coke cake center temperature in real time through an embedded thermocouple and trigger the sealing mechanism adjustment instruction when the threshold is reached.

[0031] In addition, the threshold for adjusting the equipment operating parameters is dynamically adaptable: when the environmental monitoring station detects a sudden increase in PM2.5 concentration, the temperature fluctuation threshold can be temporarily tightened through the online learning algorithm, and the original ±15°C can be adjusted to ±10°C to suppress the generation of nitrogen oxides. This threshold system is logically verified through Petri net modeling to ensure compatibility with the interlocking protection mechanism of the distributed control system (DCS). For example, when multiple thresholds trigger conflicts at the same time, the arbitration strategy will be executed according to the preset priority parameters (such as safety> environmental protection> energy efficiency).

[0032] In the above technical solution, energy switching priority refers to the fuel type switching order and proportion rules determined in a multi-energy supply system based on real-time environmental parameters, carbon emission constraints and equipment status, which is used to optimize the energy structure and reduce pollution emissions.

[0033] In the coking scenario, the coke oven heating system can adopt a mixed energy supply mode of coal gas and natural gas. The construction of the switching priority matrix needs to comprehensively consider the pollutant diffusion model, energy cost and equipment response characteristics.

[0034] For example, when the concentration of benzopyrene downwind of the plant exceeds 2.5ng / m³, the coke oven gas supply will be cut off first and the high calorific value natural gas replacement program will be started according to the characteristic vector output by the pollution reduction and carbon reduction prediction model. The switching ratio will increase in a gradient of 1:0.7 to ensure combustion stability. The design of priority rules relies on multidimensional data analysis: real-time monitoring of chimney CO through tunable diode laser absorption spectroscopy technology 2 The carbon emission intensity and thermal efficiency ratio of different energy combinations are dynamically calculated based on the power load curve recorded by the smart meter.

[0035] For example, during the low electricity demand period, waste heat boiler steam power supply may be prioritized to reduce grid dependence; and during the period when PM2.5 exceeds the standard, the proportion of natural gas is forced to increase to more than 80%. In addition, physical delays must be considered when embedding priority rules into the device control logic. For example, the response time of the gas main shut-off valve is 2 seconds. Therefore, the trend of environmental parameter changes must be predicted before the command is issued, and the switching action is triggered 1-3 sampling cycles in advance through the time series convolution network to ensure the spatiotemporal matching of command execution and pollution diffusion rate.

[0036] Furthermore, the pollution treatment node start-stop rules refer to the refined control strategies formulated based on the real-time pollution characteristics and treatment efficiency models for the operation sequence and trigger conditions of the waste gas and wastewater treatment equipment. In the coking plant, such rules cover the entire process from raw gas purification to desulfurization and denitrification, and their core is to achieve accurate start-stop of the treatment equipment through multi-source data fusion.

[0037] For example, the emergency mode start-up rules for the crude benzene scrubber stipulate that when the pressure fluctuation of the coke oven gas collecting pipe exceeds 150Pa, the high-pressure spray system must be activated 10 seconds in advance to enhance the absorption efficiency; and the regeneration cycle of the desulfurization regeneration tower is based on the H 2 The S concentration gradient is adjusted dynamically. If the UV differential absorption spectrometer detects H 2 If the S concentration rises by more than 5ppm per hour, the regeneration frequency will be increased from the default 4 hours / time to 2 hours / time. The formulation of rules relies on the analytical results of the pollution emission characteristic vector. For example, the seventh dimension characteristic value reflects the quantitative relationship between the VOCs escape rate and the coke maturity. When the value exceeds 0.85, the dry coke quenching device and the wet desulfurization tower will be started and stopped, the circulating water pump will be forced to start, and the exhaust gas residence time will be extended to 120 seconds.

[0038] In addition, the execution of rules needs to consider equipment coordination and safety redundancy: the voltage data of the electrostatic precipitator is collected every 200 milliseconds through the Modbus / TCP interface. If the deviation from the preset efficiency curve exceeds 12%, the current start-stop sequence is immediately suspended and the backup washing liquid supply pipeline is switched. All rules are certified by the safety integrity level (SIL) of the IEC 61508 standard to ensure that shutdown protection is prioritized over efficiency optimization under extreme working conditions. For example, when the dust removal fan bearing temperature is detected to exceed 90°C, the global shutdown command is immediately executed regardless of the pollution index.

[0039] The embodiments of the present invention can achieve pollution reduction and carbon reduction in industrial production in a high-quality and intelligent manner by constructing a dynamic control mechanism that integrates multi-dimensional parameters.

[0040] First, the embodiment of the present invention innovatively establishes a coupling analysis model between the equipment operation status and environmental pollutants, carbon emissions and energy flows, breaking through the limitations of traditional isolated monitoring parameters. Through the pre-trained model, multiple heterogeneous parameters are collaboratively analyzed to accurately identify the nonlinear correlation characteristics between pollution emissions and energy consumption, providing full-factor diagnostic capabilities for complex industrial scenarios.

[0041] Secondly, the embodiment of the present invention is based on a multi-level instruction generation architecture with dynamic feature vectors. By decoupling the emission reduction strategy into three interlocking dimensions of equipment operation, energy scheduling and pollution control, it achieves dynamic balance optimization of environmental protection indicators and production efficiency, and has higher system adaptability than traditional single-dimensional control methods.

[0042] Finally, the embodiment of the present invention designs a weight adjustment algorithm with self-learning ability, relying on the real-time feedback data of the Internet of Things to establish an environmental response closed loop, so that the control strategy can be autonomously optimized according to the pollutant diffusion trend and energy supply and demand fluctuations, forming an intelligent emission reduction paradigm with adaptability to spatiotemporal evolution.

[0043] In summary, the embodiments of the present invention significantly improve the coordination and sustainability of industrial emission reduction measures through mechanism fusion and dynamic optimization.

[0044] In a preferred embodiment, the process of processing the operating parameters and the environmental parameter set by the pre-trained pollution reduction and carbon reduction prediction model in S104 to output the pollution emission feature vector and dynamic emission reduction strategy of the target industrial production equipment includes: S1041: Perform time-series alignment processing on the environmental parameter set to extract the atmospheric pollutant concentration fluctuation curve, carbon emission intensity change gradient and energy consumption rate distribution matrix within the same time window.

[0045] In S1041, the industrial production monitoring device performs time-series alignment processing on the environmental parameter set of the coke oven body associated area of ​​the coke plant. For example, the β-ray absorption particulate matter monitor deployed on the coke oven chimney collects PM2.5 concentration data at a frequency of 2 times per second, while the tunable diode laser absorption spectrometer installed in the southwest corner of the plant measures CO concentration data at a period of 1 time every 5 seconds. 2 concentration.

[0046] Industrial production monitoring devices can unify parameters such as atmospheric pollutant concentrations and carbon emission intensity at different sampling frequencies onto a time reference axis of once per second through a timestamp interpolation algorithm. For example, in the time window from 10:00:00 to 10:05:00 in the morning, the instantaneous value of 0.8m / s recorded by the pusher vehicle travel speed sensor is aligned with the benzopyrene concentration of 1.8ng / m³ measured by the ultraviolet differential absorption spectrometer at the same time, forming an atmospheric pollutant concentration fluctuation curve for 60 consecutive sampling points.

[0047] At the same time, the data of smart meters distributed at three energy monitoring points in the coking plant were spatially aggregated to calculate the comprehensive power load value of the entire plant every second, and the energy consumption rate distribution matrix was constructed. The row dimension of the matrix represents energy types such as electricity and steam, and the column dimension corresponds to major energy-consuming equipment such as coke oven heating system and dust removal fan. The matrix element value represents the energy consumption proportion of each device at the current moment.

[0048] S1042: The atmospheric pollutant concentration fluctuation curve, the carbon emission intensity change gradient and the energy consumption rate distribution matrix are integrated into a multidimensional environmental state tensor, and the pollution emission characteristic vector is generated based on the multidimensional environmental state tensor and the state characteristics of the operating parameters.

[0049] In S1042, the industrial production monitoring device performs multimodal data fusion on the time-aligned environmental parameters and the coke oven body operating parameters. First, the concentration values ​​of PM2.5, benzopyrene, and hydrogen sulfide in the atmospheric pollutant concentration fluctuation curve are mapped to the three-dimensional space coordinate axes to form the spatial distribution of the pollutant concentration field. Then, the carbon emission intensity change gradient data is converted into a concentration attenuation gradient vector along the dominant wind direction of the plant. Then, the energy consumption rate distribution matrix is ​​expanded into a heat map on a two-dimensional plane, where the horizontal axis represents the time series and the vertical axis represents different energy types.

[0050] The embodiment of the present invention uses tensor splicing technology to superimpose the above three types of environmental parameters with the operating parameters of the coke oven body (including the temperature gradient of the coke tower, the opening of the gas valve, etc.) in the fourth dimension to generate a multidimensional environmental state tensor containing 12 channels. Each channel of the tensor corresponds to a specific type of working condition or environmental index. For example, the fifth channel stores the product characteristics of the travel speed of the coke pusher and the PM2.5 concentration. Based on the multidimensional environmental state tensor, the industrial production monitoring device uses a feature crossover algorithm to generate a pollution emission feature vector, in which the seventh dimension eigenvalue is obtained by calculating the Pearson correlation coefficient between the coke maturity index and the volatile organic compound escape rate, and the third dimension eigenvalue reflects the dynamic coupling strength between the regenerative chamber reversing cycle and the NOx emission.

[0051] S1043: Utilize the convolutional neural network layer in the pollution reduction and carbon reduction prediction model to extract the spatial correlation features of the multidimensional environmental state tensor, and process the spatial correlation features through the long short-term memory network layer to generate a time-dependent pollution diffusion path prediction result, and generate the dynamic emission reduction strategy based on the pollution diffusion path prediction result.

[0052] In S1043, the industrial production monitoring device calls the deep neural network in the pollution reduction and carbon reduction prediction model for feature extraction and prediction. The convolutional neural network layer first performs a three-dimensional convolution operation on the multi-dimensional environmental state tensor to identify the spatial correlation pattern between the high temperature area of ​​the coke oven combustion chamber and the PM2.5 concentration peak in the northeast corner of the plant. For example, in an operation with a convolution kernel size of 3×3×2, when it is detected that the gas valve opening exceeds 65%, the benzopyrene concentration at 800 meters from the chimney will rise by 0.3ng / m³ after 120 seconds. The long short-term memory network layer then processes the time series of the spatial correlation feature to predict the diffusion path of pollutants in the next 15 minutes.

[0053] For example, when it is identified that the coke pusher vehicle travel speed drops below 0.5 m / s and the coke cake center temperature reaches 1035 °C, the H2 in the raw coal gas is predicted. 2 The S concentration will exceed the plant boundary limit after 8 minutes, and a dynamic emission reduction strategy will be generated, including early start-up of the dry coke quenching device and a 20% increase in the washing tower spray intensity. The strategy also stipulates that if the real-time monitored steam flow rate drops by more than 10% of the rated value, it will automatically switch to the backup emission reduction plan.

[0054] S1044: Calculate the equipment operating parameter adjustment threshold in the dynamic emission reduction strategy according to the pollution diffusion path prediction result and the preset emission standard boundary conditions.

[0055] In S1044, the industrial production monitoring device matches and calculates the pollution diffusion prediction results with the environmental protection standards. When the model output shows that the PM2.5 concentration 200 meters northwest of the coke oven will exceed the national standard limit of 75μg / m³ in 300 seconds, the pollution source corresponding to the exceeded area is first identified as the failure of the riser seal of the No. 3 coke oven. By querying the equipment database, it is confirmed that the maximum allowable emission load of the pollution source equipment is 2.8kg / h, and the current real-time emission rate is 3.1kg / h. According to the adjustable parameter range specified in the equipment process manual, it is determined that the emission load can be reduced to 2.5kg / h by increasing the riser water seal height from 1200mm to 1350mm.

[0056] Furthermore, the industrial production monitoring device generates a three-stage step-by-step load reduction strategy based on the above content: in the first stage, the water seal height is increased by 50mm within 60 seconds, in the second stage, it is increased by 70mm after an interval of 90 seconds, and in the third stage, the remaining 30mm increase is dynamically adjusted according to the real-time monitoring data. At the same time, combined with the water pump energy consumption data fed back by the smart meter, the execution time interval of each stage is extended by 10 seconds to ensure the stability of the power grid, and finally the adjusted water seal height threshold and stage time parameters are written into the device control instructions.

[0057] In a preferred embodiment, the step of calculating the equipment operating parameter adjustment threshold in the dynamic emission reduction strategy according to the pollution diffusion path prediction result and the preset emission standard boundary condition in S1044 includes: S10441: Identify the target area that exceeds the emission standard boundary conditions in the pollution diffusion path prediction result and the pollution source equipment identifier associated with the target area.

[0058] In S10441, the industrial production monitoring device locates the correspondence between the pollution exceeding standard area and the pollution source through the geographic information system. When the pollution reduction and carbon reduction prediction model output shows that the concentration of benzopyrene at 500 meters downwind of the plant will exceed 2.5ng / m³ in the next 10 minutes, combined with the real-time wind speed and direction data and the historical pollution event library, it is determined that the pollution source corresponding to the exceeding standard area is the aging of the furnace door sealing strip of the No. 2 coke oven. By analyzing the equipment topology, the pollution source equipment is associated with the "coke oven body-No. 2 carbonization chamber-south furnace door", and the maintenance records of the last three months recorded in the digital twin model of the equipment are extracted to confirm that its maximum allowable leakage is 0.8m³ / min.

[0059] S10442: Extract the historical environmental parameter restoration records of the target area, and determine the equipment type, maximum emission load and adjustable operating parameter range corresponding to the pollution source equipment identification.

[0060] In S10442, the industrial production monitoring device retrieves the historical control records of the target equipment for parameter optimization. Regarding the leakage problem of the furnace door on the south side of the No. 2 coke oven, it was found that under similar working conditions last month, the leakage was successfully controlled at 0.6m³ / min by increasing the sealing strip compression force from 12MPa to 14MPa. Combined with the technical specifications provided by the equipment manufacturer, it is confirmed that the adjustable pressure range of the furnace door hydraulic adjustment system is 10-16MPa, and the response time is 45 seconds / MPa. At the same time, the coke pushing cycle parameters at the current moment are obtained to confirm that there is no planned coke pushing operation in the next 15 minutes, and there is an operating window for implementing pressure adjustment.

[0061] S10443: Based on the maximum emission load and the adjustable operating parameter range, generate a step-by-step load reduction strategy for the pollution source equipment identifier.

[0062] In S10443, the industrial production monitoring device formulates a step-by-step equipment control plan. Based on the identified leakage limit of 0.8m³ / min and the current actual value of 0.9m³ / min, it is calculated that the leakage needs to be reduced by 25%. According to the equipment adjustment characteristics, it is determined to implement pressure increase in three stages: in the first stage, the clamping force is increased from 12MPa to 13MPa within 60 seconds, and the leakage is expected to be reduced by 10%; in the second stage, it is increased to 14MPa after an interval of 120 seconds, and then reduced by 10%; the remaining 5% of the adjustment is completed dynamically in the third stage according to the real-time monitoring data. A pressure sensor calibration link is set in each stage to ensure that the single adjustment range does not exceed the equipment safety threshold.

[0063] S10444: Dynamically allocate the load reduction amplitude and time interval in the device operation parameter adjustment threshold according to the constraint relationship between the step-by-step load reduction strategy and the real-time energy consumption rate.

[0064] In S10444, the industrial production monitoring device can monitor the power load margin of the entire plant in real time in the process of coordinating energy consumption constraints and emission reduction requirements, taking into account that the hydraulic system boost operation will increase the power consumption by an additional 2.3kW. When it is found that the total load of the plant reaches 95% of the critical value when the first stage boost operation is executed, the execution interval of the second stage is automatically extended from 120 seconds to 180 seconds, and the pressure adjustment range of the third stage is reduced from 0.5MPa to 0.3MPa. Through this dynamic adjustment, the total power load is always controlled below 98% of the rated capacity.

[0065] S10445: Map the load reduction amplitude and the time interval to a device operation parameter adjustment threshold in the multi-level control instruction set.

[0066] In S10445, the industrial production monitoring device converts the optimized parameters into executable instructions. The parameters such as the pressure adjustment threshold of 13.8MPa and the stage interval of 150 seconds are encapsulated as OPC UA protocol instructions and sent to the hydraulic control system of the No. 2 coke oven through the industrial ring network. At the same time, the relevant threshold parameters are written into the interlocking protection module of the distributed control system. When the actual pressure is detected to deviate from the target value by more than 0.2MPa, the alarm is automatically triggered and the backup pressure pump is started.

[0067] In an optional embodiment, the step of generating a multi-level control instruction set for the target industrial production equipment according to the pollution emission characteristic vector and the dynamic emission reduction strategy in S106 includes: S1061: Analyze the pollution emission characteristic vector and the dynamic emission reduction strategy to identify pollution emission equipment groups and energy consumption nodes that are in an energy-wasting state.

[0068] In this embodiment, the industrial production monitoring device performs multi-dimensional analysis on the pollution emission characteristic vectors and dynamic emission reduction strategies generated by the coke oven body. Specifically, by analyzing the quantitative relationship between the volatile organic compound escape rate and the coke maturity reflected by the seventh-dimensional characteristic value, it is identified that the coke oven riser water seal device and the coke side furnace door sealing system constitute the main pollution emission equipment group.

[0069] At the same time, based on the no-load operation data of the dust removal fan in the non-coke pushing period in the energy consumption rate distribution matrix, it is determined that the equipment is in a state of energy waste. For example, when the pollution emission characteristic vector shows that the benzopyrene concentration contribution in the riser area of ​​the No. 3 coke oven reaches 68% of the total emissions, the system marks it as a key pollution source; and the dust removal fan recorded by the smart meter in the coke cake mature stage The proportion of electricity consumption exceeds the process standard value by 15%, it is identified as an energy consumption node that needs to be optimized.

[0070] S1062: Acquire the operating status data of the pollution emission equipment group, and determine the current start / stop status and processing efficiency of the pollution treatment node associated with the pollution emission equipment group based on the operating status data and the energy consumption node.

[0071] In this embodiment, the industrial production monitoring device obtains the real-time operating status of the pollution emission equipment group through the industrial bus protocol. For the identified riser water seal device, its water level sensor data, hydraulic pressure value and surrounding temperature monitoring point readings are collected to confirm that the current water seal height is maintained at 1200mm and there are small fluctuations 3 times per minute. Then the operation log of the associated crude benzene washing tower is synchronously retrieved to confirm that it is in continuous operation mode but the absorption efficiency is only 82% of the design value. By comparing the real-time processing efficiency curve with the preset emission reduction target, it is found that when the coke oven gas collecting pipe pressure exceeds 4.8kPa, the benzene removal rate of the washing tower drops to below 75%, indicating that the pollution treatment node fails to effectively match the current working condition requirements.

[0072] S1063: Generate a forced shutdown instruction, a time-limited operation window or an efficiency compensation mode in the pollution treatment node start and stop rules according to the difference between the treatment efficiency and the preset emission reduction target.

[0073] In this embodiment, the industrial production monitoring device formulates refined control rules according to the efficiency deviation of the pollution treatment node. When it is detected that the circulating gas purification efficiency of the dry coke quenching device is 10% lower than the benchmark value, the system calculates that the carbon dioxide emission equivalent per ton of coke treatment reaches 1.8kg, exceeding the preset 1.5kg low-carbon treatment threshold, and then generates a forced shutdown instruction and activates the wet desulfurization tower as a backup treatment node.

[0074] For the coke oven gas purification system in buffer operation, when the PM2.5 concentration in the southeast corner of the plant is on the rise, its limited-time operation window is dynamically allocated to the high-load production period of 08:00-12:00 every day, and the rest of the time is switched to low-power standby mode. When the steam consumption of the chemical product recovery section is lower than the design parameters but the processing efficiency meets the standard, the efficiency compensation mode is automatically enabled, and 20% of the waste heat boiler steam power is replaced by clean power input from the plant photovoltaic energy storage system.

[0075] S1064: Embed the forced shutdown instruction, the time-limited operation window or the efficiency compensation mode into the multi-level control instruction set according to priority.

[0076] In this embodiment, the industrial production monitoring device constructs a priority execution system for multi-level instructions. The forced shutdown instruction for the water seal height adjustment of the riser is set to the highest priority and embedded in the safety interlock system of the coke oven body through a hard-wired direct connection; the limited-time operation window instruction of the dust removal fan is set to a medium priority and aligned with the production schedule of the production scheduling system; the efficiency compensation mode is used as an interruptible instruction to allow the temporary suspension of the clean energy switching operation during the peak load period of the power grid. All instructions are synchronized through the time function of the OPC UA protocol to ensure that the mode switching of the relevant equipment is completed 300 seconds before the start of the coke oven pushing operation.

[0077] In an optional embodiment, the generating of the forced shutdown instruction, time-limited operation window or efficiency compensation mode in the pollution treatment node start and stop rule according to the difference between the treatment efficiency and the preset emission reduction target in S1063 includes: S10631: Monitor the real-time processing efficiency and energy consumption data of the pollution treatment node, and calculate the carbon emission equivalent of the unit pollution treatment amount of the pollution treatment node.

[0078] In this embodiment, the industrial production monitoring device monitors the operating parameters of the coking wastewater treatment station in real time. By analyzing the COD removal rate of the biochemical treatment pool and the aerator energy consumption curve, it is calculated that 2.3kg of carbon dioxide equivalent is produced for every cubic meter of wastewater treated. This value is compared with the benchmark carbon intensity of coke oven chimney emissions to evaluate the environmental performance of the wastewater treatment node. For example, when the unit denitrification power consumption of the denitrification reactor is monitored to increase by 15% year-on-year, the carbon emission equivalent recalculation process is automatically triggered to update its environmental performance rating.

[0079] S10632: If the carbon emission equivalent exceeds a preset low-carbon processing threshold, the forced shutdown instruction is triggered and the backup processing node is activated.

[0080] In this embodiment, the industrial production monitoring device performs emergency management and control of high-carbon emission equipment. When it is detected that the regeneration cycle of the wet desulfurization tower is shortened to 2 hours / time, and the carbon emission equivalent per unit sulfide treatment volume exceeds the 3.2kg threshold, a forced shutdown command is immediately issued to the DCS system. At the same time, the backup processing node is activated: the selective catalytic reduction device, and the preset ammonia injection amount compensation algorithm is used to ensure that the flue gas nitrogen oxide concentration maintains standard emissions during the equipment switching process. The shutdown command includes a three-level confirmation mechanism: first, the power supply of the desulfurization tower circulation pump is cut off, then the regeneration tower air inlet valve is closed, and finally the tower body nitrogen purge program is started.

[0081] S10633: If the carbon emission equivalent is within the preset buffer zone, the start time and duration of the time-limited operation window are dynamically allocated based on the trend of atmospheric pollutant concentrations in the current environmental parameter update set.

[0082] In this embodiment, the industrial production monitoring device implements dynamic operation window control. For the medium-temperature naphthalene removal device of the coke oven gas purification system, when its carbon emission equivalent is in the 1.6-1.8kg / m³ buffer zone, the system combines the real-time wind speed and direction data sent back by the plant weather station to allocate the device to operate only under southeast wind conditions, and the cumulative working time per day does not exceed 6 hours. For example, in the spring when the dominant wind direction is northwest wind period, the start time of the naphthalene removal device is automatically postponed to 14:00 in the afternoon, and the atmospheric diffusion conditions are used to reduce the risk of local pollutant accumulation.

[0083] S10634: If the carbon emission equivalent is lower than the low-carbon treatment threshold, but the treatment efficiency is lower than a preset reference value, then the auxiliary clean energy input ratio is increased in the efficiency compensation mode.

[0084] In this embodiment, the industrial production monitoring device optimizes the energy structure of inefficient equipment. When the processing efficiency of the oil and gas recovery device in the crude benzene section is 5% lower than the design value, but the carbon emission equivalent remains at an excellent level of 1.2kg / kg benzene series, the efficiency compensation mode is enabled. Specific measures include: switching 30% of the power of the drive motor of the washing liquid circulation pump to waste heat steam turbine power; introducing 15% of biomass gas to replace coke oven gas during the heating stage of the regeneration tower. This mode restores the equipment processing efficiency to more than 98% of the baseline value through dynamic adjustment of the energy input ratio.

[0085] S10635: Synchronize the forced shutdown instruction, the time-limited operation window or the efficiency compensation mode with the production schedule of the target industrial production equipment to generate a time-serialized start-stop rule instruction.

[0086] In this embodiment, the industrial production monitoring device realizes the deep coupling of control instructions and production plans. The forced shutdown instruction of the dry coke quenching device is time-matched with the coke pushing plan of the coke oven to ensure that the shutdown operation is performed after the current furnace chamber coke quenching operation is completed. At the same time, the time-limited operation window instruction of the wet flue gas desulfurization tower is decomposed into a microinstruction sequence with a 15-minute interval, which is precisely synchronized with the gas reversing cycle of the coke oven heating system. All start-stop rule instructions are verified by the work order management module of the production execution system (MES) to avoid conflicts with routine operations such as planned maintenance and equipment inspection.

[0087] In an optional embodiment, the dynamically adjusting the execution weight of the multi-level control instruction set based on the real-time feedback environment parameter update set in S108 includes: S1081: Receive the adjusted device operating parameters and environmental parameter update set fed back by the control terminal.

[0088] In S1081, the industrial production monitoring device receives the adjusted equipment operation parameters uploaded by the coke oven control terminal through the OPC UA protocol, including the temperature gradient distribution correction value of the No. 3 combustion chamber, the real-time measurement value of the water seal height of the riser, and the speed setting parameter of the dust removal fan inverter. At the same time, the latest environmental parameter update set uploaded by the plant environmental monitoring station is integrated, including the PM2.5 concentration decline curve recorded by the beta-ray absorption method particulate matter monitor on the southwest side, the CO concentration measured by the tunable diode laser absorption spectrometer, and the PM2.5 concentration drop curve recorded by the beta-ray absorption method particulate matter monitor on the southwest side. 2 The emission intensity is declining slowly, and the data on the increase in the steam output rate of the waste heat boiler reported by the smart meter group.

[0089] Based on this, the industrial production monitoring device uses a time series alignment algorithm to match the 0.78m / s travel speed recorded by the coke pusher positioning sensor with the benzopyrene concentration of 1.2ng / m³ detected by the ultraviolet differential absorption spectrometer at the same time, forming a device-environment association data set containing time series labels.

[0090] S1082: Calculate the deviation between the environmental parameter update set and the expected emission reduction index, and divide the weight adjustment interval according to the deviation.

[0091] In S1082, the industrial production monitoring device calculates the dynamic deviation between the environmental parameter update set and the preset emission reduction index. By comparing the percentage difference between the current PM2.5 concentration mean and the target value, and superimposing the second-order derivative of the carbon emission intensity change rate, a three-dimensional deviation evaluation matrix is ​​constructed.

[0092] For example, when the PM2.5 concentration downwind of the coke oven chimney is still 12% higher than the target value after adjustment, and the carbon emission intensity decrease rate is 30% lower than expected, the system determines that the deviation is in the second interval. The weight adjustment interval division adopts fuzzy logic algorithm, combines coke maturity index and dust removal fan energy consumption data for multi-factor coupling analysis, and determines the priority adjustment range of each control instruction.

[0093] S1083: If the deviation is in the first interval, increasing the execution weight of the energy switching priority by a fixed step size.

[0094] In S1083, the industrial production monitoring device performs a weight increment operation for the first interval deviation degree. When it is detected that the concentration of benzopyrene at the factory boundary exceeds the standard by 5%-8% and lasts for 120 seconds, the coal gas-natural gas switching priority is increased by a fixed step of 0.05 per minute.

[0095] For example, during the operation of the coke oven heating system, if the environmental parameter update set shows that the pollutant diffusion rate at the northeast monitoring point is insufficient, the system will gradually increase the execution weight of the natural gas substitution ratio from 0.65 to 0.8, forcing an increase in the supply of high calorific value clean energy. This operation is implemented through the fuel distribution module of the DCS system, and the opening and closing timing of the gas main pipeline shutoff valve and the output pressure of the natural gas pressure regulating station are synchronously adjusted.

[0096] S1084: If the deviation is in the second interval, dynamically scaling the effective ratio of the device operating parameter adjustment threshold based on the rate of change of the pollution emission characteristic vector and the adjusted device operating parameter.

[0097] In S1084, the industrial production monitoring device implements dynamic scaling control on the deviation degree of the second interval. When the actual sealing effect after the riser water seal height is adjusted deviates from the expected emission reduction target by 15%-20%, the pushing car travel speed threshold is dynamically adjusted from 0.8±0.1m / s to 0.75±0.05m / s based on the minute-level change trend of the volatile organic compound emission rate in the pollution emission characteristic vector.

[0098] At the same time, the circulating gas flow setting value of the dry coke quenching unit can be reduced by a scaling factor of 0.9 according to the real-time monitoring data of the waste heat boiler steam flow meter to ensure that the effective ratio of the equipment operation parameter adjustment threshold matches the current operating conditions. This process verifies the integrity of the control logic through the Petri net model to prevent multi-parameter adjustment from causing system oscillation.

[0099] S1085: If the deviation degree is in the third interval, the multi-level control instruction set is reset and the strategy generation process of the pollution reduction and carbon reduction prediction model is re-triggered.

[0100] In S1085, the industrial production monitoring device handles the serious deviation event in the third interval. When the environmental parameter update set shows that the CO concentration around the No. 3 coke oven rises by more than 50ppm within 300 seconds and the dynamic emission reduction strategy fails, the global control instruction set reset operation is executed. First, the gas purification system pressure adjustment instruction being executed is terminated, and then the input interface of the pollution reduction and carbon reduction prediction model is reinitialized, and the latest collected coke cake temperature distribution matrix and dust removal fan vibration spectrum data are input into the model for strategy regeneration. During the reset process, the basic safety parameters of the coke oven body are continuously monitored to ensure that the switch between the old and new instruction sets is completed within 0.5 seconds.

[0101] As an optional embodiment, the method further includes: embedding an adaptive learning module in the pollution reduction and carbon reduction prediction model, wherein the adaptive learning module is used to perform the following operations: S202: Collect the execution results of the dynamic emission reduction strategy and the corresponding environmental parameter change trajectory within the historical period.

[0102] In this embodiment, the adaptive learning module of the industrial production monitoring device collects control strategy execution data within the historical period. 368 coke pushing operation records in the past 24 hours are extracted from the coke oven operation database, including the speed adjustment value of each coke pushing vehicle, the gas valve opening change curve, and the corresponding PM2.5 concentration response data of the environmental monitoring station. At the same time, the energy consumption characteristic map of the dust removal fan under different load conditions is integrated to construct a multidimensional training data set containing timestamps, equipment status, and environmental responses.

[0103] S204: Extracting the pollution control events that do not meet the standards and the associated abnormal equipment operating parameter segments in the execution results.

[0104] In this embodiment, the industrial production monitoring device analyzes pollution control events that do not meet the standards. By comparing the preset benzopyrene concentration threshold with the actual monitoring value, three exceeding-standard events that occurred when the coke oven reversing cycle was shortened to 18 minutes were identified. Correlation analysis found that the corresponding abnormal fragments of equipment operation parameters included abnormal operating conditions such as the loss of riser water seal height monitoring data and the positioning deviation of the coke pusher exceeding 5 cm. The industrial production monitoring device extracts the coke tower temperature gradient distribution data, the raw gas flow meter readings, and the waste heat boiler steam pressure fluctuation curve within 5 minutes before and after these events to form a set of abnormal operating condition feature vectors.

[0105] S206: Convert the pollution control events and the abnormal fragments of the equipment operation parameters into model training samples, and update the feature extraction weights in the pollution reduction and carbon reduction prediction model based on the model training samples.

[0106] In this embodiment, the industrial production monitoring device converts pollution events into model training samples. For the identified riser seal failure event, the pressure fluctuation spectrum of the water seal hydraulic system during the abnormal period is extracted, and the main harmonic components are extracted as key pollution factors through Fourier transform. The feature vector containing 12 harmonic amplitudes is aligned with the benzopyrene concentration rise curve of the environmental monitoring during the same period in time and space to generate a labeled training sample set. This sample set is used to adjust the feature extraction mode of the time series convolution layer in the pollution reduction and carbon reduction prediction model.

[0107] S208: Re-evaluate the current set of environmental parameters based on the updated pollution reduction and carbon reduction prediction model and the environmental parameter change trajectory, generate an optimized dynamic emission reduction strategy and cover the multi-level control instruction set.

[0108] In this embodiment, the industrial production monitoring device uses the optimized model to regenerate the control strategy. Based on the updated feature extraction weights, the performance of the raw gas purification system under the current coke oven operation state is evaluated, and a new dynamic emission reduction strategy including dry coke quenching device frequency fine-tuning and riser water seal pressure compensation is generated. The new strategy covers the original control instruction set and is sent to the on-site actuator through the industrial wireless Mesh network. At the same time, the interlocking protection parameter database of the DCS system is updated to ensure real-time matching of the control logic and the physical characteristics of the equipment.

[0109] In detail, the updating of the feature extraction weights in the pollution reduction and carbon reduction prediction model based on the model training samples in S206 includes: S2061: Perform root cause analysis on the pollution control event to determine key pollution factors in the abnormal equipment operating parameter segment.

[0110] In S2061, the industrial production monitoring device performs root cause tracing of pollution events. A multi-dimensional analysis of the PM2.5 exceeding the standard event in the southeast corner of the coke oven was conducted, and it was determined that the key pollution factor was the instantaneous fluctuation of the air-fuel ratio in the No. 3 combustion chamber exceeding ±8%. Through correlation analysis of the equipment log, it was found that the fluctuation was caused by the malfunction of the oxygen regulating valve due to the calibration lag of the gas calorific value analyzer. The system extracts the air-fuel ratio change rate, the coke tower top temperature gradient, and the dust removal fan current fluctuation data during the abnormal period, and constructs a feature matrix containing time causal relationships.

[0111] S2062: Generate an error back propagation link between the key pollution factor and the model prediction output layer.

[0112] In S2062, the industrial production monitoring device establishes an error back-propagation link, maps the identified air-fuel ratio fluctuation factor to the PM2.5 concentration prediction error of the output layer of the pollution reduction and carbon reduction prediction model, and constructs a gradient transfer path containing a 7-layer neural network. In the back-propagation process, the focus is on correcting the response sensitivity of the time series convolution layer to the sudden change characteristics of the calorific value of coal gas, and enhancing the model's ability to capture the correlation between the combustion chamber pressure pulsation and the generation of pollutants.

[0113] S2063: Adjust the convolution kernel parameters of the convolutional neural network layer and the forgetting gate weights of the long short-term memory network layer in the pollution reduction and carbon reduction prediction model through a gradient descent algorithm.

[0114] In S2063, the industrial production monitoring device implements model parameter optimization, and uses the stochastic gradient descent algorithm to adjust the weight distribution of the 3×3×2 convolution kernel of the time series convolution layer, so that the extraction accuracy of the coke oven switching cycle and NOx emission correlation features is improved by 15%. The forget gate parameters of the long-term and short-term memory network layer are updated synchronously to reduce the memory strength of the historical invalid vibration data of the dust removal fan. The momentum factor is introduced in the parameter adjustment process to prevent the model from falling into the local optimal solution during the coke maturity feature extraction process.

[0115] S2064: Based on the set of simulated environmental parameters, determine the strategy generation accuracy of the adjusted pollution reduction and carbon reduction prediction model. If the strategy generation accuracy meets the standard, lock the target weight, otherwise roll back to the previous version of the pollution reduction and carbon reduction prediction model; wherein the target weight includes the convolution kernel parameters and the forget gate weight.

[0116] In S2064, the industrial production monitoring device can verify the effect of the model update by using a set of simulated environmental parameters for strategy generation testing, which includes artificially set boundary conditions such as sudden changes in coke oven pressure and step changes in gas calorific value. When the updated model improves the accuracy of coke cake maturity judgment to 98% and the emission reduction strategy response time is shortened to 8 seconds, the system locks the current convolution kernel parameters and forget gate weights. If the test finds that the error rate of the start and stop rule generation of the scrubber exceeds the tolerance value, it will automatically roll back to the previous version of the model and trigger an alarm to notify maintenance personnel to intervene in the calibration.

[0117] In an optional embodiment, the step of determining the strategy generation accuracy of the adjusted pollution reduction and carbon reduction prediction model based on the simulated environmental parameter set in S2064, locking the target weight if the strategy generation accuracy meets the standard, and otherwise rolling back to the previous version of the pollution reduction and carbon reduction prediction model, includes: S20641: Obtain a set of simulated environmental parameters associated with the adjusted pollution reduction and carbon reduction prediction model; wherein the set of simulated environmental parameters includes simulated atmospheric pollutant concentrations, simulated carbon emission intensity, and simulated energy consumption rate.

[0118] In the embodiment of the present invention, the industrial production monitoring device calls the simulated environment parameter generation engine to construct a test data set. The data set contains CO2 emitted from the simulated coke oven chimney. 2 Concentration fluctuation curve, PM2.5 diffusion model on the southwest side of the plant, and coke pushing operation cycle parameter combination. The simulated atmospheric pollutant concentration is generated through fluid mechanics simulation, covering the concentration gradient distribution of benzopyrene within a radius of 500 meters around the coke oven body; the simulated carbon emission intensity is based on the interpolation and reconstruction of historical production data, reflecting the unit coke carbon emission under different gas calorific value conditions; the simulated energy consumption rate is output by the equipment digital twin model, including the power consumption characteristic spectrum of the circulating fan of the dry coke quenching device under abnormal vibration state. All simulation parameters are time-series consistent with the real working condition data through the timestamp alignment algorithm, forming a set of test cases covering 72 hours of continuous working conditions.

[0119] S20642: Input the simulated environmental parameter set into the adjusted pollution reduction and carbon reduction prediction model to generate simulated pollution diffusion path prediction results and simulated dynamic emission reduction strategies.

[0120] In an embodiment of the present invention, the industrial production monitoring device inputs the simulated environmental parameter set into the updated pollution reduction and carbon reduction prediction model for strategy deduction. The pollution reduction and carbon reduction prediction model processes the operating conditions of the simulated coke oven body when the reversing cycle is shortened to 15 minutes, and generates the pollution diffusion path prediction results for the next 3 hours, showing that the PM2.5 concentration in the area covered by the dust removal fan on the northeast side will exceed the 90μg / m³ limit. The synchronously output simulated dynamic emission reduction strategy includes 12 control instructions, of which the third instruction requires the riser water seal height to be increased to 1350mm, and the fifth instruction stipulates that the natural gas emergency replacement procedure will be started when the calorific value of the coke oven gas fluctuates by more than ±5%. The model also predicts that after the implementation of this strategy, benzopyrene emissions can be reduced to 1.8ng / m³, and carbon emission intensity will be reduced by 18%.

[0121] S20643: Extracting the simulated values ​​of the equipment operating parameter adjustment thresholds and the simulated instructions for the pollution treatment node start and stop rules in the simulated dynamic emission reduction strategy.

[0122] In an embodiment of the present invention, the industrial production monitoring device extracts key parameters in the simulated dynamic emission reduction strategy, and parses the threshold simulation value of 0.72m / s from the coke pusher vehicle travel speed control instruction, which has a negative offset of 3% compared to the standard operating parameter range of 0.75-0.85m / s. The simulation instruction of the pollution treatment node start and stop rules shows that when the simulated gas collection pipe pressure reaches 5.2kPa, the crude benzene washing tower needs to enter the high-pressure spray mode 20 seconds in advance. This requirement conflicts with the 15-second buffer period specified in the current safety operating procedures. The system records such parameter deviations as feature vectors for subsequent accuracy evaluation.

[0123] S20644: According to the preset emission standard boundary conditions, the simulated value of the equipment operating parameter adjustment threshold is matched with the standard operating parameter adjustment threshold range, and the conflict status between the simulation instruction of the pollution treatment node start and stop rule and the emission reduction compliance rule is verified; the matching success rate of the simulated value of the equipment operating parameter adjustment threshold and the conflict coverage rate of the simulation instruction of the pollution treatment node start and stop rule are counted, and the strategy generation accuracy of the adjusted pollution reduction and carbon reduction prediction model is calculated based on the matching success rate and the conflict coverage rate.

[0124] In an embodiment of the present invention, the industrial production monitoring device performs strategy compliance verification. For example, the gas valve opening threshold in the simulated dynamic emission reduction strategy is compared with the process design specification, and it is found that the fourth stage opening adjustment value exceeds the mechanical limit of the equipment by 2.3 percentage points. At the same time, it is detected that the execution of the start and stop rules of the dry coke quenching device in the simulation environment will cause the dust removal fan load rate to exceed the rated value, triggering the safety interlock protection mechanism. The system calculates that the matching success rate of the simulated value of the equipment operating parameter adjustment threshold is 87.5%, and the conflict coverage rate of the simulated instructions of the pollution treatment node start and stop rules is 14.3%. The overall strategy generation accuracy is 82.6%.

[0125] S20645: If the strategy generation accuracy exceeds the preset accuracy threshold, the target weights in the adjusted pollution reduction and carbon reduction prediction model are locked to the current convolution kernel parameters and the current forgetting gate weights; if the strategy generation accuracy does not exceed the accuracy threshold, the convolution kernel parameters and forgetting gate weights of the previous version of the pollution reduction and carbon reduction prediction model are loaded from the model version library, and the parameters of the adjusted pollution reduction and carbon reduction prediction model are overwritten.

[0126] In an embodiment of the present invention, the industrial production monitoring device performs model parameter management according to the accuracy threshold: when the measured accuracy of 82.6% exceeds the preset 80% qualification line, the convolution kernel parameters of the current version are locked, and the distribution pattern of [0.78, -0.23, 0.45] in the third-layer convolution kernel weight matrix is ​​permanently saved. The forget gate weight of the long short-term memory network layer is adjusted from 0.32 to 0.28 to enhance the memory capacity of sudden changes in coke maturity events. If the accuracy rate does not meet the standard, the previous model parameters are restored from the version library, including rolling back the [0.65, 0.12, -0.09] weight configuration of the second temporal convolution layer.

[0127] S20646: Synchronize the locked target weights or the rolled-back convolution kernel parameters and forget gate weights to the online prediction interface of the pollution reduction and carbon reduction prediction model, so that the subsequent pollution diffusion path prediction results and the generation of dynamic emission reduction strategies are consistent with the updated model parameters.

[0128] In the embodiment of the present invention, the industrial production monitoring device completes the model parameter synchronization operation, writes the locked convolution kernel parameters into the GPU acceleration module of the prediction model through the encrypted channel, and updates the weight configuration file of the online interface at the same time. The updated model is immediately applied to real-time data processing. When the temperature of the regenerator of the No. 2 coke oven is detected to fluctuate abnormally, the new convolution kernel can accurately identify the operating condition and the raw gas H 2 The correlation characteristics of the increased S concentration are used to generate an optimization strategy including compensation for the ammonia injection amount.

[0129] In another optional embodiment, the step of acquiring the set of environmental parameters in S102 includes: S1021: Collecting raw data on atmospheric pollutant concentrations in real time through a gas sensor network deployed in the associated area.

[0130] In an embodiment of the present invention, the industrial production monitoring device collects environmental data through a distributed gas sensor network. For example, 8 sets of beta-ray absorption particulate matter monitors deployed on the top of the coke oven body measure the instantaneous concentration of PM2.5 during the coke pushing process at a frequency of 6 times per minute. 12 ultraviolet differential absorption spectrometers set up at the boundary of the plant continuously scan the concentration distribution of benzopyrene and generate a three-dimensional pollution diffusion heat map every 10 seconds. All monitoring equipment transmits raw data through an industrial wireless mesh network, using time division multiple access technology to avoid channel conflicts.

[0131] S1022: Extracting the hourly carbon emission intensity and energy consumption rate log of the target industrial production equipment from the energy management platform.

[0132] In the embodiment of the present invention, the industrial production monitoring device is connected to the data interface of the energy management platform, and the accumulated value of gas flow is extracted from the PLC of the coke oven heating system, and the carbon emission intensity per minute is calculated in combination with the coke output. The smart meter group records the power consumption curve of major equipment such as dust removal fans and circulating water pumps with an accuracy of 0.5 seconds, and the steam flow meter synchronously uploads the output data of the waste heat boiler. The system establishes a three-dimensional matrix of energy consumption rate, with the horizontal axis being the equipment number, the vertical axis being the time series, and the depth axis distinguishing energy types such as electricity and steam.

[0133] S1023: Perform noise filtering and outlier removal on the raw data of atmospheric pollutant concentration, the hourly carbon emission intensity and the energy consumption rate log to generate a preprocessing environmental parameter set.

[0134] In the embodiment of the present invention, the industrial production monitoring device performs data cleaning preprocessing, uses a sliding window filtering algorithm to eliminate instantaneous pulse interference in PM2.5 monitoring data, and identifies and removes abnormal gas calorific value sampling points through box plot analysis. For the high-frequency noise data falsely reported by the dust removal fan vibration sensor, wavelet transform is applied to reconstruct the signal to restore the true load fluctuation characteristics. The preprocessed environmental parameter set retains 98.7% of the valid data points, forming a continuous and complete time series data set.

[0135] S1024: Align the preprocessing environment parameter set by timestamp and compress it into a target transmission format; wherein the target transmission format matches the pollution reduction and carbon reduction prediction model.

[0136] In the embodiment of the present invention, the industrial production monitoring device completes the data format standardization, unifies the PM2.5 concentration, carbon emission intensity and other parameters of different sampling frequencies to a time base of 1 per second, and uses the HDF5 format for lossless compression. The data packet header embeds meta-information such as the device number and checksum, and is encapsulated into a 128-dimensional feature vector that meets the input requirements of the pollution reduction and carbon reduction prediction model through the industrial bus protocol. The size of each data packet is controlled within 512 bytes to ensure real-time transmission efficiency.

[0137] In another optional embodiment, the method further includes: deploying a policy execution monitoring module in the control terminal, wherein the policy execution monitoring module performs the following operations: S302: Parse the received multi-level control instruction set, and decompose the multi-level control instruction set into operation codes that meet the device execution condition.

[0138] In S302, the strategy execution monitoring module of the industrial production monitoring device parses the multi-level control instructions and converts the air-fuel ratio optimization instructions of the coke oven combustion chamber into PID parameter adjustment codes executable by the PLC, including 32 operating parameters such as the oxygen flow valve opening gradient and the gas pressure compensation coefficient. The coke pusher travel speed control instructions are disassembled into the bottom-level execution codes such as the servo motor speed setting value and the track positioning verification frequency, and each code is accompanied by a safety verification mark.

[0139] S304: Monitor the actual parameter adjustment range and energy consumption change curve of the operation code during the operation of the device.

[0140] In S304, the industrial production monitoring device monitors the execution effect of the instruction in real time, tracks the actual speed curve of the coke pusher through the laser displacement sensor, compares it with the target value of 0.75m / s required by the control instruction, and calculates the instantaneous speed deviation value. The output current waveform of the dust removal fan inverter is collected synchronously to analyze whether the energy consumption change trend meets the expected power saving target. All monitoring data are refreshed in a period of 200ms to form an execution effect evaluation matrix with a timestamp.

[0141] S306: If it is detected in combination with the energy consumption change curve that the deviation between the actual parameter adjustment range and the instruction requirement exceeds the fault tolerance threshold, a device operation status rollback mechanism is triggered.

[0142] In S306, the industrial production monitoring device handles the execution deviation exceeding the standard event. When it is detected that the actual value of the water seal height adjustment of the riser lags behind the command target by 120mm and continues to exceed the target for 30 seconds, the three-level rollback mechanism is triggered: first, the hydraulic system pressure is restored to the safe reference value, then the integral term of the water seal height control loop is reset, and finally the intelligent positioning module is restarted. During the rollback process, the sealing performance indicators are continuously monitored to ensure that the pollutant escape rate does not exceed the emergency threshold.

[0143] S308: Feedback the reason code of the equipment operation status rollback mechanism and the corrected parameter adjustment value to the pollution reduction and carbon reduction prediction model.

[0144] In S308, the industrial production monitoring device implements a feedback loop, packages the rollback reason code "E0452" of the riser seal failure event and the corrected hydraulic pressure setting value into a feedback data packet, and uploads it to the pollution reduction and carbon reduction prediction model through the OPC UA protocol. The model's adaptive learning module adjusts the confidence weight of the water seal height control strategy accordingly, and increases the safety margin design of the pressure compensation coefficient when the next strategy is generated.

[0145] As an alternative but non-limiting embodiment, the method of using the convolutional neural network layer in the pollution reduction and carbon reduction prediction model in S1043 to extract the spatial correlation features of the multidimensional environmental state tensor, and processing the spatial correlation features through the long short-term memory network layer to generate a time-dependent pollution diffusion path prediction result, and generating the dynamic emission reduction strategy based on the pollution diffusion path prediction result includes: S10431: Perform a multi-scale convolution kernel sliding scan on the multi-dimensional environmental state tensor to generate a spatial feature map containing a local pollutant distribution pattern.

[0146] In S10431, a multi-scale convolution kernel scanning operation is performed on the multi-dimensional environmental state tensor constructed in the associated area of ​​the coke oven body of the coke plant. The tensor integrates twelve dimensions of environmental and operating parameters, such as the temperature gradient distribution of the coke oven combustion chamber, the time series data of the coke pusher's travel speed, and the PM2.5 concentration heat map at the plant boundary. A 3×3×2 convolution kernel is used to perform a sliding scan along the time axis to identify the spatial correlation pattern between the abnormal temperature fluctuation in the coke oven riser area and the peak value of benzopyrene concentration on the southwest side. For example, when the convolution kernel scans that the temperature of the No. 3 combustion chamber exceeds 1050℃ and the gas valve opening is at the critical value of 65% during the same period, the activation value of the corresponding position in the output feature map is significantly increased, marking the area as a volatile organic compound escape heat point.

[0147] S10432: Perform a cross-channel maximum pooling operation on the spatial feature map to compress redundant noise and retain the spatial correlation features in the local pollutant distribution pattern.

[0148] In S10432, for the three-dimensional pollutant concentration field formed by the exhaust gas flow from the coke oven chimney, the pooling layer screens the peak response characteristics in each channel to suppress the noise interference caused by the vibration of the dust removal fan. For example, during the coke oven reversing cycle, the pooling operation retains the fluctuation of the calorific value of the gas and the CO 2 The strong correlation features of the emission gradient are removed, while transient outliers caused by steam pressure fluctuations are filtered out. The dimension of the feature map after pooling compression is reduced to 30% of the original data, but the retention rate of key spatial correlation features exceeds 95%.

[0149] S10433: Input the spatial correlation features into the long short-term memory network layer in the order of time windows, capture the attenuation gradient of pollutant concentration in adjacent time windows through the gating mechanism, and generate a time-dependent pollutant diffusion intensity sequence.

[0150] In S10433, the industrial production monitoring device inputs the spatial correlation features into the long-short-term memory network layer for time series processing. The network forget gate dynamically adjusts the influence weight of the coke oven historical operation data. When it is detected that the coke pusher's travel speed is lower than 0.7m / s for three consecutive cycles, the memory strength of the coke cake maturity parameters is enhanced. The update gate adjusts the feature transfer ratio according to the real-time relationship between the current dust removal fan load rate and the pollutant diffusion rate. The output gate generates a pollutant diffusion intensity sequence for the next 15-minute time window, accurately reflecting the attenuation gradient of benzopyrene concentration under the dominant wind direction in the plant area.

[0151] S10434: Perform regional superposition calculations based on the pollutant diffusion intensity sequence and the preset diffusion coefficient matrix to predict the migration path and concentration accumulation area of ​​pollutants in multiple subsequent monitoring cycles, and generate the time-dependent pollution diffusion path prediction result.

[0152] In S10434, the industrial production monitoring device combines the atmospheric diffusion coefficient matrix to predict the pollution path. The diffusion intensity sequence output by the long short-term memory network is tensor-multiplied with the real-time wind speed and direction data of the meteorological station to draw the migration trajectory of PM2.5 particles in the next three hours. The prediction results show that when the speed of the dust removal fan on the northeast side of the coke oven drops to 85% of the rated value, the coking benzene series will form a concentration accumulation area 800 meters downwind. The system simultaneously generates a heat map of the pollution diffusion path containing latitude and longitude coordinates and concentration thresholds, marking the red warning area that exceeds the 50μg / m³ limit.

[0153] S10435: Extract the critical area exceeding the preset concentration threshold in the pollution diffusion path prediction result, and reversely match the adjustable parameter items in the operating parameters according to the pollution source equipment identifier associated with the critical area.

[0154] In S10435, when the predicted path shows that the concentration of benzopyrene at 200 meters around the riser of the No. 3 coke oven will exceed 2.5ng / m³ in 8 minutes, the industrial production monitoring device traces back to the operating parameters of the electric tar collector of the gas purification system. Through the equipment topology relationship mapping, the adjustable parameter items of the current electric tar collector secondary voltage fluctuation exceeding ±5% are identified and associated with the gas flow mutation event caused by the compression of the coke pushing cycle.

[0155] S10436: Based on the operational constraints of the adjustable parameter items and the historical adjustment effectiveness data, generate a set of candidate emission reduction strategies that include parameter adjustment sequence and amplitude combinations; perform multi-objective optimization sorting of the candidate emission reduction strategy set in terms of energy consumption rate and emission reduction efficiency, and select the strategy that meets the preset carbon emission intensity reduction rate and has the highest energy switching priority as the dynamic emission reduction strategy.

[0156] In S10436, for the voltage adjustment item of the electrostatic precipitator, three candidate solutions were selected based on historical control records: immediately increase the voltage to 45kV, adjust it to 42kV in stages, or switch to the backup power supply line. The multi-objective optimization algorithm evaluates the comprehensive performance of each solution. When the energy consumption growth rate of Solution 2 is controlled at 8% and the benzene removal rate is increased by 23%, it is marked as the optimal strategy. The final dynamic emission reduction strategy includes voltage adjustment instructions, coke pusher speed reduction compensation measures, and dust removal fan frequency conversion coordination parameters.

[0157] S10437: Verify the spatiotemporal alignment of the dynamic emission reduction strategy with the pollutant migration path in the pollution diffusion path prediction result. If there is an uncovered pollutant accumulation area, the strategy supplement mechanism is triggered to add a regional coordinated emission reduction instruction to the dynamic emission reduction strategy.

[0158] In S10437, after the industrial production monitoring device implemented the dynamic emission reduction strategy, real-time monitoring showed that there was still an unexpected accumulation of VOCs concentration in the crude benzene section area on the southeast side. The system immediately triggered the supplementary mechanism and issued additional instructions requiring the oil and gas recovery device in the chemical product recovery section to start the high-pressure absorption mode 30 seconds in advance and increase the washing liquid circulation flow to 115% of the design value. The supplementary instructions were synchronously sent to the on-site PLC controller through the OPC UA protocol to ensure that the newly added pollution accumulation area was effectively controlled within 120 seconds.

[0159] As another alternative but non-limiting embodiment, the step of synchronizing the forced shutdown instruction, the time-limited operation window or the efficiency compensation mode with the production schedule of the target industrial production equipment in S10635 to generate a time-series start-stop rule instruction includes: S106351: Analyze the process segment nodes and production batch timestamps in the production schedule of the target industrial production equipment, and extract the production schedule node set; wherein the production schedule node set includes the equipment startup time, the raw material delivery cycle and the finished product output time interval.

[0160] In S106351, the industrial production monitoring device analyzes the coke oven production schedule and extracts the current production batch data from the manufacturing execution system, including the planned coke pushing time of the No. 2 carbonization chamber at 10:15:00 and the reversing period of the No. 3 combustion chamber at 08:30-09:45. When constructing the production schedule node set, the coke tower coal loading timestamp, the raw gas export stage mark and the finished coke output time interval are synchronously integrated to form a time-space matrix containing 78 process segment nodes.

[0161] S106352: Traverse the forced shutdown instructions, time-limited operation windows or efficiency compensation modes in the pollution treatment node start and stop rules, and identify the pollution treatment node identifier and start and stop action type corresponding to each start and stop rule.

[0162] In S106352, the industrial production monitoring device matches the start-stop rules with the equipment identification, and identifies that the equipment number corresponding to the forced shutdown instruction of the dry coke quenching device is DJQ-03, the limited-time operation window instruction is associated with the dust removal fan CF-07, and the efficiency compensation mode acts on the crude benzene washing tower XB-12. Each start-stop rule is attached with an action type code, such as the forced shutdown instruction is marked as an L1-level interruption operation, and the limited-time operation window is defined as a T2-level deferred action.

[0163] S106353: Match the pollution treatment node identifier with the equipment start time in the production scheduling node set to determine the execution time constraint of the start / stop action type in the production scheduling node set; wherein the execution time constraint includes the earliest trigger time and the latest completion time allowed for start / stop.

[0164] In S106353, it was found that the start and stop of crude benzene washing tower XB-12 needs to be implemented during the stable pressure stage of the coke oven gas collecting pipe, which corresponds to the 09:00-09:15 process window in the production schedule. The system sets the earliest triggering time of this instruction to be 30 seconds after the pressure stabilizes (09:00:30), and the latest completion time shall not be later than 60 seconds before the next batch of coal loading operation (09:14:00).

[0165] S106354: Generate an execution time window for the forced shutdown instruction, time-limited operation window or efficiency compensation mode according to the execution time constraint and the priority order of the start / stop action type; wherein the start time of the execution time window is no earlier than the earliest trigger time of the allowed start / stop and the end time is no later than the latest completion time.

[0166] In S106354, the time-limited operation window instruction of the dust removal fan CF-07 is allocated to the execution period of 10:05-10:25 in combination with the finished product output gap period of the production schedule. The start time of this window is 10 seconds later than the coke pushing completion signal of the No. 2 coke oven (10:05:10), and the end time is 300 seconds earlier than the reversing preparation stage of the No. 3 combustion chamber (10:22:00), ensuring that there is no conflict with the key production process.

[0167] S106355: Extract the energy consumption peak interval corresponding to the raw material delivery cycle in the production scheduling node set, perform overlapping analysis on the execution time window and the energy consumption peak interval, and adjust the starting time of the execution time window to avoid conflict with the energy consumption peak interval.

[0168] In S106355, industrial production monitoring devices can avoid energy consumption peaks. For example, if it is detected that the power load of the entire plant will reach its peak during the raw material delivery cycle of 10:00-10:15, the forced shutdown instruction execution window of the dry coke quenching unit DJQ-03 is adjusted from the original 10:10-10:30 to 10:16-10:36. The start time of the adjusted window is delayed by 6 minutes to avoid the maximum power consumption period of the raw material conveyor belt unit, ensuring that the power grid stability indicators meet safety regulations.

[0169] S106356: Generate a timestamp instruction chain of the forced shutdown instruction, time-limited operation window or efficiency compensation mode according to the adjusted execution time window and the finished product output time interval in the production scheduling node set; wherein each instruction in the timestamp instruction chain includes a target pollution treatment node identifier, a start / stop action type and an execution timestamp.

[0170] In S106356, the industrial production monitoring device can construct a timestamp instruction chain. For example, the efficiency compensation mode of the crude benzene washing tower XB-12 is decomposed into three sub-instructions: start the high-pressure pump at 09:00:30, adjust the pH value of the washing liquid at 09:05:00, and activate the standby absorption tower at 09:10:15. Each instruction is embedded in the process gap of the production schedule. For example, the start time of the high-pressure pump is scheduled 15 seconds after the temperature measurement operation of the coke tower is completed to avoid resource competition with the core production process.

[0171] S106357: Map the timestamp instruction chain to the equipment operating parameter adjustment threshold of the production scheduling node set, and verify whether the execution timestamp in the timestamp instruction chain causes the equipment operating parameters to exceed the equipment operating parameter adjustment threshold; if exceeded, reallocate the starting time of the execution time window.

[0172] It is understandable that this step involves verification of parameter threshold compliance. For example, it is detected that the pH value adjustment instruction at 09:05:00 will cause the scrubber pressure to instantly exceed the upper limit of the equipment operation parameter adjustment threshold by 0.5MPa, and the industrial production monitoring device automatically postpones the execution time to 09:06:30. When the reallocated instruction is triggered, the corresponding coke oven gas collecting pipe pressure is in the falling stage, leaving sufficient safety margin for parameter adjustment.

[0173] S106358: Generate a time-serialized start-stop rule instruction sequence based on the verified timestamp instruction chain and the production batch timestamps in the production scheduling node set; wherein the start-stop rule instruction sequence is arranged in the order of production batch timestamps, and the triggering time of each instruction is embedded in the process segment node gap of the production scheduling node set.

[0174] In S106358, the industrial production monitoring device performs the steps of generating the final start-stop rule sequence, such as arranging the instructions according to the production batch timeline to ensure that the dust removal fan time limit instruction at 10:16:00 is fully executed before the reversing preparation stage of combustion chamber 3. The timestamp of each instruction is precisely aligned with the clock reference of the DCS system, with the deviation controlled within ±50ms, and the time synchronization function of the industrial bus protocol is used to achieve coordinated operation of the equipment in the entire plant.

[0175] See also Figure 2 As shown, this figure is a schematic diagram of the basic structure of an industrial production monitoring device 200 provided by an embodiment of the present invention. The industrial production monitoring device 200 includes: Processor 201; a storage device 202 on which a computer program 2020 is stored; When the computer program 2020 is executed by the processor 201, the processor 201 implements any of the industrial production monitoring methods for reducing pollution and carbon emissions in the ecological environment.

[0176] Based on the above, a readable storage medium is provided, on which a program or instruction is stored, and when the program or instruction is executed by a processor, the steps of the above method are implemented.

[0177] It should be noted that the various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments, and the same or similar parts between the various embodiments can be referred to each other. For the system or device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description.

Claims

1. An industrial production monitoring method for ecological environmental pollution reduction and carbon reduction, characterized in that: include: Obtaining operating parameters of target industrial production equipment and a set of environmental parameters of associated areas, wherein the set of environmental parameters includes atmospheric pollutant concentration, carbon emission intensity, and energy consumption rate; Processing the operating parameters and the environmental parameter set through a pre-trained pollution reduction and carbon reduction prediction model, and outputting the pollution emission feature vector and dynamic emission reduction strategy of the target industrial production equipment; Generate a multi-level control instruction set for the target industrial production equipment according to the pollution emission characteristic vector and the dynamic emission reduction strategy, wherein the multi-level control instruction set includes equipment operation parameter adjustment thresholds, energy switching priorities, and pollution treatment node start and stop rules; The multi-level control instruction set is transmitted to the control terminal of the target industrial production equipment through the Internet of Things interface, and the execution weight of the multi-level control instruction set is dynamically adjusted based on the real-time feedback environmental parameter update set.

2. The method according to claim 1, characterized in that The process of processing the operating parameters and the environmental parameter set by the pre-trained pollution reduction and carbon reduction prediction model to output the pollution emission feature vector and dynamic emission reduction strategy of the target industrial production equipment includes: Performing time series alignment processing on the environmental parameter set to extract the atmospheric pollutant concentration fluctuation curve, carbon emission intensity change gradient and energy consumption rate distribution matrix within the same time window; The atmospheric pollutant concentration fluctuation curve, the carbon emission intensity change gradient and the energy consumption rate distribution matrix are merged into a multidimensional environmental state tensor, and the pollution emission feature vector is generated based on the multidimensional environmental state tensor and the state characteristics of the operating parameters; The convolutional neural network layer in the pollution reduction and carbon reduction prediction model is used to extract the spatial correlation features of the multidimensional environmental state tensor, and the spatial correlation features are processed through the long short-term memory network layer to generate a time-dependent pollution diffusion path prediction result, and the dynamic emission reduction strategy is generated based on the pollution diffusion path prediction result; According to the pollution diffusion path prediction result and the preset emission standard boundary conditions, the equipment operation parameter adjustment threshold in the dynamic emission reduction strategy is calculated.

3. The method according to claim 2, characterized in that The calculating, according to the pollution diffusion path prediction result and the preset emission standard boundary condition, the equipment operation parameter adjustment threshold in the dynamic emission reduction strategy includes: Identifying a target area that exceeds the boundary conditions of the emission standard in the pollution diffusion path prediction result and a pollution source equipment identifier associated with the target area; Extract the historical environmental parameter restoration records of the target area, and determine the equipment type, maximum emission load and adjustable operating parameter range corresponding to the pollution source equipment identification; Based on the maximum emission load and the adjustable operating parameter range, generating a step-by-step load reduction strategy for the pollution source equipment identifier; According to the constraint relationship between the step-by-step load reduction strategy and the real-time energy consumption rate, dynamically allocating the load reduction amplitude and time interval in the device operation parameter adjustment threshold; The load reduction amplitude and the time interval are mapped to a device operation parameter adjustment threshold in the multi-level control instruction set.

4. The method according to claim 1, characterized in that: The step of generating a multi-level control instruction set for the target industrial production equipment according to the pollution emission characteristic vector and the dynamic emission reduction strategy includes: Analyzing the pollution emission characteristic vector and the dynamic emission reduction strategy to identify pollution emission equipment groups and energy consumption nodes in an energy-wasting state; Acquire the operation status data of the pollution emission equipment group, and determine the current start / stop status and treatment efficiency of the pollution treatment node associated with the pollution emission equipment group based on the operation status data and the energy consumption node; According to the difference between the treatment efficiency and the preset emission reduction target, generating a forced shutdown instruction, a time-limited operation window or an efficiency compensation mode in the pollution treatment node start and stop rules; embedding the forced shutdown instruction, the time-limited operation window or the efficiency compensation mode into the multi-level control instruction set according to priority; The generating of a forced shutdown instruction, a limited time operation window or an efficiency compensation mode in the pollution treatment node start and stop rule according to the difference between the treatment efficiency and the preset emission reduction target includes: Monitor the real-time processing efficiency and energy consumption data of the pollution treatment node, and calculate the carbon emission equivalent of the unit pollution treatment amount of the pollution treatment node; If the carbon emission equivalent exceeds a preset low-carbon processing threshold, the forced shutdown instruction is triggered and the backup processing node is activated; If the carbon emission equivalent is within the preset buffer zone, the start time and duration of the time-limited operation window are dynamically allocated according to the trend of atmospheric pollutant concentration in the current environmental parameter update set; If the carbon emission equivalent is lower than the low-carbon treatment threshold, but the treatment efficiency is lower than a preset reference value, then the auxiliary clean energy input ratio is increased in the efficiency compensation mode; The forced shutdown instruction, the time-limited operation window or the efficiency compensation mode are synchronized with the production schedule of the target industrial production equipment to generate a time-serialized start-stop rule instruction.

5. The method according to claim 1, characterized in that The updating set of environmental parameters based on real-time feedback dynamically adjusts the execution weight of the multi-level control instruction set, including: Receiving an updated set of adjusted equipment operating parameters and environmental parameters fed back by the control terminal; Calculating the deviation between the environmental parameter update set and the expected emission reduction index, and dividing the weight adjustment interval according to the deviation; If the deviation is in the first interval, increasing the execution weight of the energy switching priority by a fixed step size; If the degree of deviation is in the second interval, dynamically scaling the effective ratio of the device operating parameter adjustment threshold based on the rate of change of the pollution emission characteristic vector and the adjusted device operating parameter; If the degree of deviation is in the third interval, the multi-level control instruction set is reset and the strategy generation process of the pollution reduction and carbon reduction prediction model is re-triggered.

6. The method according to claim 1, characterized in that The method further comprises: An adaptive learning module is embedded in the pollution reduction and carbon reduction prediction model, and the adaptive learning module is used to perform the following operations: Collect the execution results of the dynamic emission reduction strategy and the corresponding environmental parameter change trajectory within the historical period; Extracting the pollution control events that do not meet the standards and the associated abnormal equipment operation parameter fragments in the execution results; Converting the pollution control events and the abnormal fragments of the equipment operation parameters into model training samples, and updating the feature extraction weights in the pollution reduction and carbon reduction prediction model based on the model training samples; Re-evaluate the current set of environmental parameters based on the updated pollution reduction and carbon reduction prediction model and the environmental parameter change trajectory, generate an optimized dynamic emission reduction strategy and cover the multi-level control instruction set; The updating of the feature extraction weights in the pollution reduction and carbon reduction prediction model based on the model training samples includes: Conduct root cause analysis on the pollution control events to determine key pollution factors in the abnormal equipment operating parameter segments; Generate an error back propagation link between the key pollution factor and the model prediction output layer; Adjusting the convolution kernel parameters of the convolutional neural network layer and the forget gate weights of the long short-term memory network layer in the pollution reduction and carbon reduction prediction model by a gradient descent algorithm; Based on a set of simulated environmental parameters, the strategy generation accuracy of the adjusted pollution reduction and carbon reduction prediction model is determined. If the strategy generation accuracy meets the standard, the target weight is locked, otherwise it is rolled back to the previous version of the pollution reduction and carbon reduction prediction model; wherein the target weight includes the convolution kernel parameters and the forget gate weight.

7. The method according to claim 6, characterized in that The method of determining the strategy generation accuracy of the adjusted pollution reduction and carbon reduction prediction model based on the simulated environmental parameter set, and locking the target weight if the strategy generation accuracy meets the standard, or rolling back to the previous version of the pollution reduction and carbon reduction prediction model, includes: Acquire a set of simulated environmental parameters associated with the adjusted pollution reduction and carbon reduction prediction model; wherein the set of simulated environmental parameters includes simulated atmospheric pollutant concentration, simulated carbon emission intensity and simulated energy consumption rate; Inputting the simulated environmental parameter set into the adjusted pollution reduction and carbon reduction prediction model to generate simulated pollution diffusion path prediction results and simulated dynamic emission reduction strategies; Extracting the equipment operation parameter adjustment threshold simulation value and the pollution treatment node start-stop rule simulation instruction in the simulated dynamic emission reduction strategy; According to the preset emission standard boundary conditions, the simulated value of the equipment operating parameter adjustment threshold is matched with the standard operating parameter adjustment threshold interval, and the conflict status between the pollution treatment node start and stop rule simulation instruction and the emission reduction compliance rule is verified; the matching success rate of the simulated value of the equipment operating parameter adjustment threshold and the conflict coverage rate of the pollution treatment node start and stop rule simulation instruction are counted, and the strategy generation accuracy of the adjusted pollution reduction and carbon reduction prediction model is calculated based on the matching success rate and the conflict coverage rate; If the strategy generation accuracy exceeds the preset accuracy threshold, the target weight in the adjusted pollution reduction and carbon reduction prediction model is locked to the current convolution kernel parameters and the current forget gate weight; if the strategy generation accuracy does not exceed the accuracy threshold, the convolution kernel parameters and forget gate weight of the previous version of the pollution reduction and carbon reduction prediction model are loaded from the model version library, and the parameters of the adjusted pollution reduction and carbon reduction prediction model are overwritten; The locked target weights or the rolled-back convolution kernel parameters and forget gate weights are synchronized to the online prediction interface of the pollution reduction and carbon reduction prediction model, so that the subsequent pollution diffusion path prediction results and the generation of dynamic emission reduction strategies are consistent with the updated model parameters.

8. The method according to claim 1, characterized in that The step of obtaining the environmental parameter set includes: Collecting raw data of atmospheric pollutant concentrations in real time through a gas sensor network deployed in the associated area; Extracting hourly carbon emission intensity and energy consumption rate logs of the target industrial production equipment from the energy management platform; Perform noise filtering and outlier removal on the raw data of atmospheric pollutant concentration, the hourly carbon emission intensity and the energy consumption rate log to generate a preprocessing environmental parameter set; The pre-processing environment parameter set is aligned by timestamp and compressed into a target transmission format; wherein the target transmission format matches the pollution reduction and carbon reduction prediction model.

9. The method according to claim 1, characterized in that: The method further comprises: A policy execution monitoring module is deployed in the control terminal, and the policy execution monitoring module performs the following operations: Parsing the received multi-level control instruction set, and disassembling the multi-level control instruction set into operation codes that meet the device execution conditions; Monitor the actual parameter adjustment range and energy consumption change curve of the operation code during the operation of the device; If it is detected in combination with the energy consumption change curve that the deviation between the actual parameter adjustment range and the instruction requirement exceeds the fault tolerance threshold, the device operation status rollback mechanism is triggered; The reason code of the equipment operation status rollback mechanism and the corrected parameter adjustment value are fed back to the pollution reduction and carbon reduction prediction model.

10. An industrial production monitoring device, characterized in that: include: processor; A storage device having a computer program stored thereon, wherein when the computer program is executed by the processor, the processor implements the industrial production monitoring method for ecological environmental pollution reduction and carbon reduction as described in any one of claims 1 to 9.

Images