A customized energy-saving air conditioner control method and device for industrial process requirements

Abstract

The application provides a customized energy-saving air conditioner control method and device for industrial process requirements, and applies to the technical field of data processing. The application removes electromagnetic interference and vibration noise by Kalman filtering, generates a standardized process-environment-energy consumption correlation sequence, and then converts it into a three-dimensional process load spectrum. Through fluid dynamics simulation and adaptive grid division, a personalized air conditioner dynamic load prediction model is established combined with the scene thermal and humid characteristics. The process priority factor is extracted to construct the adjustment matrix, and the air conditioner parameter combination under the target energy consumption is calculated. At the same time, the energy consumption characteristics are extracted to divide the over-standard risk level and build a multi-dimensional feature matrix. The real-time and historical data are compared to identify abnormalities, and the energy consumption optimization correction factor is generated. According to the enterprise situation, the users are grouped, the key factors are selected by gradient boosting tree, the personalized energy-saving control model is constructed by fusing multiple information, the target parameters are output, and the real-time adjustment instructions and time-sharing energy-saving strategies are generated.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, in particular to a customized energy-saving air conditioner control method and device for industrial process requirements. BACKGROUND

[0002] In the field of industrial production, air conditioning systems, as key equipment to ensure process stability, have a high proportion of energy consumption in the total industrial energy consumption. Therefore, it is of great significance to achieve energy-saving control under the premise of meeting process requirements. However, the existing industrial air conditioning control technology has the following shortcomings:

[0003] There are a large number of electromagnetic interferences (such as electromagnetic signals generated by equipment such as machine tools and frequency converters) and equipment vibration noises (such as vibration when punch presses and fans are running) in industrial environments. These interferences can cause distortion of collected process parameters, environmental data and energy consumption data, making the basic data for air conditioning control inaccurate, thereby affecting the adjustment accuracy and making it difficult to meet the stringent requirements of high-precision processes on temperature and humidity (such as electronic component welding, food baking, etc.).

[0004] Most existing air conditioning load prediction models are designed based on general scenarios, without fully considering the differences in thermal and humidity characteristics of different industrial processes (such as the thermal and humidity requirements of mechanical processing workshops and textile printing and dyeing workshops, which are completely different), and the lack of detailed analysis of high-load process areas, resulting in large deviations between predicted results and actual loads, and unable to provide accurate basis for energy-saving control.

[0005] There is a lack of systematic evaluation of energy consumption exceeding the standard, making it difficult to identify abnormal situations such as short-term energy consumption surge and imbalance between load and energy consumption in advance. At the same time, there is no dynamic correction mechanism for energy consumption optimization based on real-time working conditions. When process parameters or environmental conditions change, air conditioning operating parameters cannot be adjusted in time, resulting in energy waste or failure to meet process requirements.

[0006] Industrial enterprises differ significantly in production scale, process complexity and equipment configuration (such as the difference in air conditioning requirements between small-scale mechanical processing enterprises and large-scale automobile manufacturing enterprises). Existing control models mostly use uniform parameter settings, without customized design for the characteristics of different user groups, resulting in difficulty in balancing energy-saving effect and process adaptability.

[0007] It should be noted that the information disclosed in the above background section is only used to strengthen the understanding of the background of the present disclosure, and therefore can include information that does not constitute prior art known to those of ordinary skill in the art. SUMMARY

[0008] Other characteristics and advantages of the present application will become apparent from the following detailed description, or will be learned by practice of the application.

[0009] According to an aspect of the present application, a customized energy-saving air conditioner control method for industrial process requirements is provided, comprising: obtaining real-time process parameters, environmental data and air conditioner operation history energy consumption archives of industrial production, using Kalman filtering algorithm to eliminate industrial environment electromagnetic interference and equipment vibration noise, and generating standardized process-environment-energy consumption correlation data sequence; after converting the standardized process-environment-energy consumption correlation data sequence into a three-dimensional process load distribution map, processing by fluid dynamics simulation software, selecting adaptive grid division algorithm for subdivision of high-load process area, combining the differences in thermal and humid characteristics of different industrial scenes, and constructing an individualized air conditioner dynamic load prediction model; based on the individualized air conditioner dynamic load prediction model, extracting priority factors of different industrial processes to construct a dynamic parameter adjustment matrix, performing parallel calculation on the air conditioner multi-module operation state, and obtaining air conditioner operation parameter combination under target energy consumption; extracting energy consumption peak, load fluctuation rate, process-energy consumption matching difference value according to industrial process scene, dividing energy consumption over-standard risk level, and constructing a multi-dimensional feature matrix containing process demand intensity, environmental interference coefficient and equipment energy efficiency attenuation information; comparing real-time energy consumption with historical same period same process data to identify abnormal signals of short-term energy consumption sudden increase and load-energy consumption matching imbalance, using energy consumption-process parameter correlation curve slope to generate energy consumption optimization dynamic correction factor; grouping users according to industrial enterprise production scale, process complexity and equipment configuration, using gradient boosting tree algorithm to screen key influence factors of multi-dimensional feature matrix and energy consumption optimization dynamic correction factor, and constructing personalized energy-saving control model by fusing energy consumption optimization parameters, process constraint conditions and equipment operation limit information; based on the target operation parameter output of the personalized energy-saving control model, combining the time correlation information of industrial process time sequence arrangement and air conditioner equipment operation characteristics, generating real-time dynamic adjustment instructions and time-sharing energy-saving control strategy.

[0010] In another aspect of the present application, a customized energy-saving air conditioner control device for industrial process requirements comprises: an acquisition module for acquiring real-time process parameters, environmental data and air conditioner operation history energy consumption archives of industrial production, removing industrial environment electromagnetic interference and equipment vibration noise by using Kalman filtering algorithm, and generating standardized process-environment-energy consumption correlation data sequence; a processing module for converting the standardized process-environment-energy consumption correlation data sequence into a three-dimensional process load distribution map, processing by fluid dynamics simulation software, selecting adaptive grid division algorithm for subdivision of high-load process area, combining differences in thermal and humidity characteristics of different industrial scenes, and constructing an individualized air conditioner dynamic load prediction model; extracting priority factors of different industrial processes based on the individualized air conditioner dynamic load prediction model to construct a dynamic parameter adjustment matrix, performing parallel calculation on air conditioner multi-module operation state, and obtaining air conditioner operation parameter combination under target energy consumption; extracting energy consumption peak value, load fluctuation rate and process-energy consumption matching difference value according to industrial process scene, dividing energy consumption over-standard risk level, and constructing a multi-dimensional feature matrix containing process demand intensity, environmental interference coefficient and equipment energy efficiency attenuation information; comparing real-time energy consumption with historical same-period same-process data, identifying abnormal signals of short-term energy consumption surge and load-energy consumption matching imbalance, and generating energy consumption optimization dynamic correction factor by using energy consumption-process parameter correlation curve slope; grouping users according to industrial enterprise production scale, process complexity and equipment configuration, selecting key influence factors of multi-dimensional feature matrix and energy consumption optimization dynamic correction factor by using gradient boosting tree algorithm, and constructing personalized energy-saving control model by fusing energy consumption optimization parameters, process constraint conditions and equipment operation limit information; generating real-time dynamic adjustment instructions and time-of-day energy-saving control strategies based on target operation parameter output of the personalized energy-saving control model, and combining time correlation information of industrial process time sequence arrangement and air conditioner equipment operation characteristics.

[0011] According to still another aspect of the present application, an electronic device comprises: a first processor; and a memory for storing executable instructions of the first processor; wherein the first processor is configured to execute the above-mentioned customized energy-saving air conditioner control method for industrial process requirements by executing the executable instructions.

[0012] According to still another aspect of the present application, a computer readable storage medium is provided, which stores a computer program, and the computer program is executed by a second processor to implement the above-mentioned customized energy-saving air conditioner control method for industrial process requirements.

[0013] The application provides an industrial process demand-oriented customized energy-saving air conditioner control method and device.

[0014] It should be understood that the foregoing general description and the following detailed description are only exemplary and explanatory and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF DRAWINGS

[0015] Figure 1 A flowchart of an industrial process demand-oriented customized energy-saving air conditioner control method provided by an embodiment of the application is shown.

[0016] Figure 2 A structural schematic diagram of an industrial process demand-oriented customized energy-saving air conditioner control device provided by an embodiment of the application is shown. DETAILED DESCRIPTION

[0017] The preferred embodiments of the present application are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to explain and illustrate the present application and are not used to limit the present application.

[0018] The industrial process demand-oriented customized energy-saving air conditioner control method according to the exemplary embodiments of the present application is described below in conjunction with Figure 1 It should be noted that the following application scenarios are only shown for the purpose of facilitating the understanding of the spirit and principles of the present application, and the embodiments of the present application are not limited in this respect. On the contrary, the embodiments of the present application are applicable to any applicable scenarios.

[0019] In one embodiment, the present application further provides an industrial process demand-oriented customized energy-saving air conditioner control method and device. Figure 1 A flowchart of an industrial process demand-oriented customized energy-saving air conditioner control method according to an embodiment of the present application is shown.

[0020] S101, obtain industrial production real-time process parameters, environmental data and air conditioning operation history energy consumption archives, adopt Kalman filtering algorithm to eliminate industrial environment electromagnetic interference and equipment vibration noise, and generate standardized process-environment-energy consumption correlation data sequence.

[0021] In an embodiment, the industrial production real-time process parameters are indexes reflecting the core state of the industrial production process, and key parameters need to be determined according to different industrial scenes and collected in real time. For example, in the mechanical processing scene, the real-time process parameters to be collected include machine tool cutting speed (m / min), feed amount (mm / r), and cutting depth (mm), which directly affect the heat generation in the processing area, and then correlate the air conditioning load demand; in the electronic component welding scene, the real-time process parameters include welding temperature (℃), welding time (s), and solder supply amount (g / s), and excessive welding temperature will cause the local environment temperature to rise sharply, which needs to be adjusted in time by the air conditioning system. The collection method can be real-time monitoring by industrial sensors, such as installing a rotating speed sensor on the machine tool spindle and a temperature sensor at the welding station, and the sensor data is transmitted in real time to the data collection terminal through the industrial bus (Profinet).

[0022] The environmental data needs to be collected around the key environmental factors affecting the operation of the air conditioning system in the industrial space, to ensure that the data can reflect the actual state of the industrial environment. For example, in the automobile painting workshop, the environmental data to be collected include the temperature (℃) in the workshop, the relative humidity (%RH), and the air cleanliness (particles / m³, counting the number of particles greater than 0.5 μm), the temperature and humidity will directly affect the drying effect of the paint, and the air cleanliness is related to the painting quality, which all need to be adjusted by the air conditioning system according to the actual situation; in the food processing workshop, the environmental data also need to increase the air pressure (Pa) in the workshop to avoid the entry of external pollutants into the clean processing area. When collecting, temperature and humidity sensors, dust particle counters, and air pressure sensors can be arranged in different areas of the workshop (such as the painting station, the drying area, and the corner of the workshop), and the sensors collect data every 10 seconds to ensure real-time reflection of environmental changes.

[0023] The air conditioning operation history energy consumption archive needs to collect the energy consumption data of the air conditioning system during the past operation process, providing historical reference for subsequent energy consumption analysis and optimization. Taking the central air conditioning energy saving project of a machinery manufacturing enterprise as an example, the historical energy consumption archive to be obtained includes the daily power consumption (kWh) of the air conditioner in the past 12 months, the energy consumption data under different operation modes (such as refrigeration, heating, ventilation), the individual energy consumption records of each module of the air conditioner (such as compressor, fan, water pump), and the association of the corresponding time period production process information (such as daily processing product type, production time) and environmental data (such as daily average temperature, humidity), and the historical association between energy consumption and process, environment. The acquisition method is to export through the historical database of the air conditioning control system. If the air conditioning system does not have a built-in historical data storage function, an intelligent electric meter and an energy consumption monitoring module are added to collect the energy consumption data of the past period of time, ensuring that the data time span is long enough to cover the energy consumption under different seasons and different production loads.

[0024] There are a lot of electromagnetic interference (such as electromagnetic signals generated by machine tools, frequency converters and other equipment) and equipment vibration noise (such as sensor data fluctuation caused by vibration of punch press and fan during operation) in industrial environment. These interferences will cause the collected data to be distorted, and Kalman filtering algorithm needs to be used to process the data to eliminate the interference and ensure the accuracy of the data. Taking the air conditioning data processing of a steel rolling workshop in a steel plant as an example, strong electromagnetic interference will be generated when the rolling mill runs in the workshop, causing the temperature data collected by the temperature and humidity sensor to fluctuate irregularly (such as the actual temperature stabilizing at 28℃, the sensor data randomly fluctuating between 26-30℃); at the same time, the vibration of the fan and rolling mill in the workshop will cause the power consumption data collected by the energy consumption sensor to have instantaneous abnormal values (such as normal energy consumption of 50kWh / h, occasionally 80kWh / h of instantaneous data).

[0025] When using Kalman filtering algorithm, first, the system state equation and observation equation are established: the true values of temperature and energy consumption are taken as the system state, and the interference data collected by the sensor are taken as the observation value; then through the prediction step, the system state and error covariance at the current time are predicted according to the optimal estimation value at the last time; then through the update step, the Kalman gain is calculated by combining the observation value at the current time and the prediction error, and the predicted value is corrected to obtain the optimal estimation value at the current time. For example, for temperature data, the fluctuating data of 26-30℃ is corrected to accurate data stabilizing at about 28℃ after Kalman filtering, and the fluctuation amplitude is controlled within ±0.5℃; for energy consumption data, the instantaneous abnormal 80kWh / h data is corrected to a reasonable range of 50-52kWh / h, effectively eliminating the influence of electromagnetic interference and vibration noise.

[0026] After completing data collection and interference elimination, the process parameters, environmental data, and energy consumption data need to be standardized and the correlation between them needs to be established to form a standardized process-environment-energy consumption correlation data sequence, ensuring uniform data format and clear logical correlation, which facilitates subsequent atlas conversion and model construction. Data standardization needs to convert data of different dimensions and units into standard data of a uniform order of magnitude, eliminating dimensional effects. Taking the air conditioning data of an electronics factory as an example, the welding temperature in the original data is 220-250℃, the workshop temperature is 25-30℃, and the air conditioning power consumption is 80-120kWh / h, with large differences in units and value ranges. The Min-Max standardization method is used to map all data to the [0, 1] interval, and the standardization formula is: standardized data = (original data - minimum data) / (maximum data - minimum data). For example, the welding temperature of 220℃ corresponds to a standardized value of 0, 250℃ corresponds to a standardized value of 1, and 235℃ is calculated as (235-220) / (250-220) = 0.5; the workshop temperature of 25℃ corresponds to 0, the workshop temperature of 30℃ corresponds to 1, and the workshop temperature of 27.5℃ is standardized to 0.5; the air conditioning power consumption of 80kWh / h corresponds to 0, the air conditioning power consumption of 120kWh / h corresponds to 1, and the air conditioning power consumption of 100kWh / h is standardized to 0.5.

[0027] The correlation between process, environment, and energy consumption data is established according to the time dimension, ensuring that the three types of data at the same time node correspond to each other, forming a correlation data sequence. Taking the processed data with a time interval of 1 hour as an example, in the standardized data at a certain time (e.g., 9:00-10:00 on May 10, 2024), the welding temperature standardized value is 0.5, the workshop temperature standardized value is 0.5, and the air conditioning power consumption standardized value is 0.5. These three data are associated in the order of "process parameter-environment data-energy consumption data" to form the correlation data group at that time (0.5, 0.5, 0.5). The correlation data groups at different times (e.g., 9:00-10:00, 10:00-11:00, 11:00-12:00, etc.) are sequentially arranged to generate a standardized process-environment-energy consumption correlation data sequence, such as [(0.5, 0.5, 0.5), (0.6, 0.6, 0.6), (0.4, 0.4, 0.4),...], which clearly reflects the correspondence between process, environment, and energy consumption at different time points, laying the foundation for subsequent conversion to a three-dimensional process load distribution atlas.

[0028] S102, after converting the standardized process-environment-energy consumption correlation data sequence into a three-dimensional process load distribution atlas, processing it with a fluid dynamics simulation software, and selecting an adaptive grid division algorithm to subdivide the high-load process area, an individualized air conditioning dynamic load prediction model is constructed based on the differences in thermal and humidity characteristics of different industrial scenarios.

[0029] In an embodiment, the standardized process-environment-energy consumption correlation data sequence is converted into a three-dimensional process load distribution map to generate the basic load visualization data. When constructing the three-dimensional process load distribution map, first, each item of data in the standardized process-environment-energy consumption correlation data sequence needs to be processed according to a clear dimension mapping rule: the process parameter is mapped to the X axis, the environmental data is mapped to the Y axis, and the energy consumption data is mapped to the Z axis, thereby constructing a multi-dimensional correlation visualization map and generating the basic load visualization data. Under this rule, each data group in the sequence will correspond to a data point in the map. Taking an electronic component welding workshop as an example, in the standardized process-environment-energy consumption correlation data sequence of the electronic component welding workshop, the data group of a certain period of time is (welding temperature standardized value 0.6, workshop temperature standardized value 0.5, air conditioner power consumption standardized value 0.7), and according to the above mapping rule, the corresponding coordinates of this data group in the three-dimensional map are (X=0.6, Y=0.5, Z=0.7). By mapping the coordinates of all data groups in the sequence one by one (such as (0.5, 0.4, 0.6), (0.7, 0.6, 0.8), etc.), a complete three-dimensional process load distribution map is finally formed. In this map, the higher the Z axis value represents the higher the energy consumption, and the changes in the X axis and Y axis values reflect the fluctuations in the process parameters and environmental conditions, respectively. By observing the map, it can be directly found that when the welding temperature is raised (the X axis increases) + the workshop temperature is raised (the Y axis increases), the energy consumption (Z axis) usually rises in association. This visualization presentation makes the basic load data more intuitive and helps to quickly locate the specific process and environmental combination that leads to high energy consumption.

[0030] The three-dimensional process load distribution map is imported into the fluid dynamics simulation software for simulation calculation to generate the thermal and humid load field simulation data. To generate the thermal and humid load field simulation data, the three-dimensional process load distribution map needs to be imported into the fluid dynamics simulation software (such as Fluent, STAR-CCM+) for simulation calculation. During the simulation process, the fluid dynamics simulation software simulates the air flow trajectory in the industrial space, the thermal and humid exchange efficiency, and combines the load distribution in the three-dimensional map to quantify the thermal and humid load intensity of different process areas, and finally calculates and outputs the thermal and humid load values of each process area. Taking an automobile painting workshop as an example, first, the three-dimensional process load distribution map of the workshop (X axis is the painting line running speed, Y axis is the workshop temperature and humidity, and Z axis is the air conditioning energy consumption) is imported into the Fluent software; then a physical model completely consistent with the actual workshop (size 40m x 20m x 8m, including 3 painting lines and 2 drying areas) is built in the software; then the data in the three-dimensional map is accurately associated with the corresponding areas of the physical model (for example, the area with painting line No. 1 running speed X = 0.8 and workshop humidity Y = 0.6 corresponds to high energy consumption data Z = 0.9); after starting the software simulation calculation, the software simulates the complete flow trajectory of the air in the workshop from the air inlet to the air outlet (such as forming vortex near the drying area, resulting in longer air residence time), and quantifies the thermal and humid exchange efficiency of different areas (such as the thermal exchange efficiency of the drying area reaching 90%, and the thermal exchange efficiency of the ordinary painting area being about 60%); finally, the thermal and humid load field simulation data is generated, which clearly shows that the thermal and humid load intensity of the drying area is 80 W / ㎡, which is much higher than that of the ordinary painting area of 40 W / ㎡, clearly presenting the load difference of different process areas.

[0031] In order to accurately analyze the thermal and humidity load field simulation data and distinguish the load differences in different areas, an adaptive grid division algorithm is used to subdivide the high-load process area in the thermal and humidity load field simulation data, and then generate differentiated grid data. In this process, the adaptive grid division algorithm can identify the thermal and humidity load density in the thermal and humidity load field simulation data in real time. When the load density exceeds the preset threshold, the grid refinement mechanism will be automatically triggered. At the same time, the grid resources are configured in accordance with the core rule of "high-density grid for high-load area and low-density grid for low-load area". In specific implementation, the load density threshold is first set by the algorithm, and then the grid division operation is carried out based on the threshold. Taking the mechanical processing workshop as an example, the thermal and humidity load density threshold is set to 60 W / ㎡. Then the algorithm identifies the load density in the thermal and humidity load field simulation data in real time. From the data, it can be clear that the lathe processing area is a high-load process area with a load density of 75 W / ㎡ (exceeding the preset threshold), and the warehouse area has a load density of 30 W / ㎡ (lower than the preset threshold). According to the above grid division rule, the algorithm triggers the grid refinement for the lathe processing area and configures a high-density grid of 2 cm×2 cm×2 cm. This precision grid can accurately capture the local load fluctuations (such as the load density near the spindle position reaching 85 W / ㎡ and the edge area being 65 W / ㎡) caused by the heat generated by machine tool cutting in the lathe processing area. For the low-load warehouse area, a low-density grid of 10 cm×10 cm×10 cm is used, which can only reflect the overall stable low load state of the warehouse area. In the final differentiated grid data, the number of grids in the high-load lathe processing area is 5000, and the number of grids in the low-load warehouse area is only 800. While ensuring the calculation accuracy of the high-load area, the overall data volume is greatly reduced, providing efficient and accurate data support for the construction of individualized air conditioning dynamic load prediction model.

[0032] To precisely adapt to the air conditioning control requirements of different industrial scenarios, the thermal and humidity characteristic difference parameters of different industrial scenarios need to be collected first, and then the scenario-based thermal and humidity characteristic constraint library is constructed based on these parameters, and then the scenario constraint data is generated. Take the food baking workshop and the textile printing and dyeing workshop as examples: for the food baking workshop, first collect the thermal and humidity characteristic difference parameters of the dough fermentation stage: the temperature needs to be stable at 28-30℃, the relative humidity needs to be maintained at 70%-75%, and the temperature fluctuation is too large, which will lead to uneven fermentation of the dough (the maximum tolerance fluctuation is ±1℃), and the humidity fluctuation is too large, which will affect the quality of the dough (the maximum tolerance fluctuation is ±3%RH), and these parameters are entered into the scenario-based thermal and humidity characteristic constraint library as exclusive constraint items for this scenario; for the textile printing and dyeing workshop, collect the thermal and humidity characteristic difference parameters of the cloth dyeing stage: the temperature needs to be controlled at 60-65℃, the relative humidity needs to be maintained at 50%-55%, because the cloth has strong resistance to high temperature (the temperature fluctuation range is ±2℃), the humidity fluctuation has a relatively mild effect on dyeing uniformity (the allowed range is ±5%RH), and it is found that "the humidity drops more than 5%RH / h during dyeing will cause uneven dyeing of the cloth", so this special constraint item is added and also entered into the constraint library. In the finally constructed scenario-based thermal and humidity characteristic constraint library, each industrial scenario corresponds to a set of exclusive constraint parameters, and the generated scenario constraint data can clearly and explicitly indicate the thermal and humidity boundary conditions that the air conditioning system needs to meet in different scenarios, providing scenario-based constraint basis for the construction of subsequent individualized air conditioning dynamic load prediction models.

[0033] Fusion of differentiated grid data and scenario constraint data, construction of individualized air conditioning dynamic load prediction model. Model construction needs to extract the load characteristics (such as the load intensity and fluctuation law of each grid) from the differentiated grid data, and then integrate the boundary conditions in the scenario constraint data to establish a "load-scenario constraint" correlation prediction logic. Take the food baking workshop as an example: first extract the load characteristics of the high-density grid in the fermentation area from the differentiated grid data: the fermentation area load intensity is stable at 55-60W / ㎡ during the day (8:00-18:00) (due to continuous fermentation heat production), and drops to 30-35W / ㎡ at night (18:00-8:00 the next day) (fermentation is suspended); then integrate the conditions "temperature 28-30℃, humidity 70%-75%, temperature fluctuation ±1℃" from the scenario constraint data, and establish the prediction logic: when the model predicts that the fermentation area load rises to 58W / ㎡, if the current workshop temperature has reached 29.5℃ (close to the upper limit of the constraint), the air conditioning load needs to be increased by 10% to control the temperature not to exceed 30℃; if the current temperature is 28.5℃, the air conditioning load needs to be increased by 5% to maintain the temperature stable. Through this integration, the constructed individualized air conditioning dynamic load prediction model can accurately predict the air conditioning load demand in different time periods and different areas according to the grid load changes and thermal and humidity constraints of the baking workshop, such as predicting that the air conditioning load needs to be maintained at 120kW during the daytime fermentation peak period, and can be reduced to 80kW at night.

[0034] S103, based on the individual air conditioning dynamic load prediction model, the priority factors of different industrial processes are extracted to construct a dynamic parameter adjustment matrix, and the air conditioning multi-module operation state is calculated in parallel to obtain the air conditioning operation parameter combination under the target energy consumption.

[0035] In an embodiment, based on the individual air conditioning dynamic load prediction model, the priority factors of different industrial processes are extracted to construct a dynamic parameter adjustment matrix. The priority factor extraction takes the production criticality, thermal and humid demand urgency, and energy consumption sensitivity of the industrial process as the core dimension. The dynamic parameter adjustment matrix associates and maps the priority factors of each process with the air conditioning adjustment parameters to generate a parameter adjustment logic framework that can be updated in real time. To achieve precise dynamic adjustment of air conditioning parameters, the priority factors of different industrial processes need to be extracted based on the individual air conditioning dynamic load prediction model, and a dynamic parameter adjustment matrix needs to be constructed. Among them, the priority factor extraction takes the production criticality, thermal and humid demand urgency, and energy consumption sensitivity of the industrial process as the core dimension, and needs to combine the load characteristics (such as the load intensity and fluctuation law of each process area) output by the individual air conditioning dynamic load prediction model to quantitatively assign each core dimension. Taking an automobile parts production workshop as an example, the workshop includes engine cylinder body processing (process A), parts cleaning (process B), and finished product assembly (process C). Combined with the load characteristics output by the model, the quantitative assignment of each dimension is as follows:

[0036] Production criticality: The load characteristics of process A (engine cylinder body processing) show that it is extremely sensitive to temperature fluctuations, and temperature deviation will directly cause processing precision failure, thereby causing the entire engine to be scrapped. The production criticality is assigned a value of 0.9 (full score 1.0). The load characteristics of process B (cleaning) show that humidity fluctuations only indirectly affect the cleanliness of parts, and the degree of influence on the final product quality is moderate. The production criticality is assigned a value of 0.6. The load characteristics of process C (assembly) show that it has a relaxed requirement for temperature and humidity, and the production criticality is the lowest, assigned a value of 0.3.

[0037] Thermal and humid demand urgency: The load characteristics of process A show that it needs to maintain the workshop temperature at 20±1℃ and the relative humidity at 50±5%, and a temperature deviation of 1℃ will trigger load abnormalities, which need to be adjusted immediately. The thermal and humid demand urgency is assigned a value of 0.8. The load characteristics of process B allow a small amplitude fluctuation within a short time (such as 10 minutes) in the temperature range of 25±2℃ and the humidity range of 60±8%. The urgency is assigned a value of 0.5. The load characteristics of process C have no strict immediate adjustment requirement for temperature and humidity, and only need to be maintained at 18-28℃ and 40-70% RH. The urgency is assigned a value of 0.2.

[0038] Energy consumption sensitivity: The load characteristics of process A show that a 5% reduction in air conditioning energy consumption will directly lead to a decrease in temperature control accuracy, exceeding the allowable range of the process, making it extremely sensitive to changes in energy consumption, with a sensitivity value of 0.9; the load characteristics of process B show that an 8% reduction in energy consumption can still maintain a normal thermal and humidity environment, with a sensitivity value of 0.5; the load characteristics of process C show that a 15% reduction in energy consumption will only have a slight impact on the environment, with a sensitivity value of 0.2. Based on the above quantification, the priority factors for the three types of processes are: process A (0.9, 0.8, 0.9), process B (0.6, 0.5, 0.5), and process C (0.3, 0.2, 0.2).

[0039] The dynamic parameter adjustment matrix is ​​input into the parallel computing module to synchronously calculate the operating status of multiple air conditioning modules and generate multiple sets of candidate operating parameters. The parallel computing module adopts a distributed computing architecture and performs parameter iteration calculations simultaneously based on the independent operating characteristics and interactive influence relationships of each air conditioning module. The dynamic parameter adjustment matrix needs to map the priority factors of each process with the air conditioning adjustment parameters (such as compressor frequency, fan speed, air supply temperature, and air supply humidity) to clarify the logic that "the higher the priority, the higher the priority of air conditioning parameter adjustment" and support real-time updates. Taking the automotive parts workshop as an example, the matrix rows represent process types (processes A, B, and C), the columns represent "priority factor dimensions + air conditioning adjustment parameters", and the matrix elements are the association weights (the higher the weight, the more sensitive the parameter adjustment is to the priority of the process): the association weight of "production criticality (0.9)" and "air supply temperature adjustment" of process A is set to 0.8, which means that when the production criticality of process A triggers the adjustment demand, the air supply temperature is adjusted first; its "heat and humidity demand urgency (0.8)" and "compressor frequency adjustment" association weight is set to 0.7 to ensure rapid temperature stabilization. For process B, the correlation weight between "urgency of heat and humidity demand (0.5)" and "supply air humidity adjustment" is set to 0.6, as the cleaning process is more sensitive to humidity; the correlation weight between "energy consumption sensitivity (0.5)" and "fan speed adjustment" is set to 0.5, balancing energy consumption and process requirements. For process C, the correlation weights between each priority factor and air conditioning parameter are all set to 0.3, with minor adjustments only made without affecting processes A and B. This matrix can automatically update the correlation weights based on real-time process load changes (e.g., an increase in the number of processing batches in process A, raising the production criticality to 0.95), generating a real-time adjustable parameter adjustment logic framework.

[0040] After the dynamic parameter adjustment matrix is completed, the dynamic parameter adjustment matrix needs to be input into the parallel computing module, and the running state of the air conditioning multi-module is calculated synchronously by the parallel computing module, and finally a plurality of candidate running parameter sets are generated. Among them, the parallel computing module adopts a distributed computing architecture (such as a distributed node based on Hadoop), and in the calculation process, the air conditioning multi-module will be first disassembled into independent computing nodes (compressor node, fan node, humidity adjustment node), and then according to the independent running characteristics (such as the compressor frequency only affects the refrigerating capacity, the fan speed only affects the air supply rate) and the interaction influence relationship (such as the increase of the fan speed will increase the energy consumption and may affect the optimal value of the compressor frequency) of each air conditioning module, the parameter iteration operation is carried out at the same time, so as to ensure the calculation efficiency and the parameter adaptability.

[0041] Taking the air conditioning system (including 1 compressor, 2 air supply fans, and 1 humidifier) of an automobile parts workshop as an example: the parallel computing module distributes the correlation weights in the dynamic parameter adjustment matrix to the corresponding independent computing nodes. According to the correlation weight of “process A heat and humidity demand urgency (0.8)” in the matrix, the compressor frequency candidate values (50 Hz, 55 Hz, 60 Hz) are preliminarily calculated; according to the correlation weight of “process B air supply humidity demand”, the fan speed candidate values (1200 r / min, 1400 r / min, 1600 r / min) are calculated; and according to the correlation weight of “process B humidity demand”, the humidification amount candidate values (2 kg / h, 3 kg / h, 4 kg / h) are calculated. In the iteration operation process, each node synchronously interacts data through distributed communication, and fully considers the interaction influence relationship between the modules: when the compressor frequency is set to 60 Hz (strong refrigeration), the fan node will optimize the speed candidate value to 1600 r / min according to the interaction logic of “strong refrigeration needs to improve the air supply efficiency to uniformly cool down”, and the humidifier node will correspondingly reduce to 2 kg / h to avoid low humidity; if the compressor frequency is 50 Hz (weak refrigeration), the fan node does not need high speed to meet the air supply demand, and maintains 1200 r / min, and the humidifier node can maintain 3 kg / h.

[0042] After a plurality of rounds of such iterative optimization parameter combination, the parallel computing module finally outputs a plurality of candidate running parameter sets, and each parameter set includes the running parameters of all modules of the air conditioner. For the above workshop, the core candidate set is 3 sets: candidate set 1: compressor frequency 60 Hz, fan speed 1600 r / min, humidification amount 2 kg / h (preferentially meeting the high criticality demand of process A); candidate set 2: compressor frequency 55 Hz, fan speed 1400 r / min, humidification amount 3 kg / h (balancing the demands of processes A and B); and candidate set 3: compressor frequency 50 Hz, fan speed 1200 r / min, humidification amount 4 kg / h (preferentially controlling energy consumption and meeting the basic demands of processes B and C).

[0043] Based on the preset target energy consumption threshold, the candidate operating parameter set is screened and optimized to obtain the air conditioner operating parameter combination under the target energy consumption. The screening process constructs a dual-objective evaluation function of energy consumption and process satisfaction, introduces parameter sensitivity analysis, and pre-judges the energy consumption impact of slight fluctuations of key adjustment parameters. The target energy consumption threshold is preset in combination with the enterprise energy saving target and the process energy consumption benchmark. Taking an automobile parts workshop as an example, according to historical data and energy saving requirements, the target energy consumption threshold of the air conditioning system of the workshop is set to 120 kWh / h (10 hours of daily production, daily energy consumption not exceeding 1200 kWh). In order to achieve the best balance between energy saving and process protection, a dual-objective evaluation function considering “energy consumption compliance degree” and “process satisfaction degree” is constructed. The simplified formula of the function is: evaluation score = (1-actual energy consumption / target energy consumption threshold) x 0.5 + process satisfaction degree x 0.5 (full score 1.0, score≥0.8 is qualified), wherein the “process satisfaction degree” is calculated by comparing the deviation of the heat and humidity output corresponding to the air conditioning parameters and the process demand (for example, process A requires temperature 20±1℃, parameter output temperature 20.2℃, satisfaction degree 0.98).

[0044] The function is used to evaluate and screen 3 groups of candidate parameter sets. Specifically, candidate set 1: actual energy consumption 135 kWh / h (exceeds threshold), energy consumption compliance degree -0.06, process satisfaction degree 0.95, evaluation score 0.415 (unqualified, rejected). Candidate set 2: actual energy consumption 118 kWh / h (lower than threshold), energy consumption compliance degree≈0.008, process satisfaction degree 0.92, evaluation score≈0.468 (qualified). Candidate set 3: actual energy consumption 105 kWh / h (lower than threshold), energy consumption compliance degree=0.0625, process satisfaction degree 0.85, evaluation score=0.4875 (qualified). Through preliminary screening, candidate set 2 and candidate set 3 are retained.

[0045] To ensure that the selected parameter combination has good stability and robustness, parameter sensitivity analysis is introduced. The analysis aims to pre-judge the potential impact of slight fluctuations of key adjustment parameters (such as compressor frequency, fan speed) on energy consumption and process satisfaction, and prevent the system from deviating from the optimal state or violating the constraints due to slight disturbances. Take candidate set 2 (compressor frequency 55 Hz, fan speed 1400 r / min) as an example for sensitivity analysis. Compressor frequency analysis: if the frequency increases from 55 Hz to 56 Hz (fluctuation 1.8%), the energy consumption increases to 122 kWh / h (exceeds threshold), although the process satisfaction increases to 0.93, but the risk of energy consumption exceeding the threshold increases significantly, so the frequency should be limited to not exceed 55 Hz.

[0046] For fan speed analysis, if the speed decreases from 1400 r / min to 1350 r / min (fluctuation 3.6%), the energy consumption decreases to 115 kWh / h, and the process meets the degree of 0.89 (still qualified), and the speed is optimized to 1350 r / min. According to the comprehensive evaluation and sensitivity analysis results, the final optimal air conditioning operation parameter combination is: compressor frequency 55 Hz, fan speed 1350 r / min, humidification amount 3 kg / h. Under this combination, the energy consumption is 115 kWh / h (lower than the threshold), and the process meets the degree of 0.89, which realizes the effective balance of energy saving and process demand.

[0047] In one embodiment, the energy consumption peak value, load fluctuation rate and process-energy consumption matching difference value are extracted according to the industrial process scene, and a multi-dimensional feature matrix containing process demand intensity, environmental interference coefficient and equipment energy efficiency attenuation information is constructed.

[0048] In one embodiment, the energy consumption peak value, load fluctuation rate and process-energy consumption matching difference value are extracted according to the industrial process scene, and energy consumption feature data is generated. The energy consumption peak value is the maximum value of air conditioning energy consumption per unit time corresponding to the process scene. The "unit time" for statistics should be determined according to the process running period to ensure that the peak value can accurately reflect the highest energy consumption demand in this scene. Taking a plastic injection molding workshop as an example, the process running period of this workshop is 1 hour (including injection molding heating, mold cooling, product taking out and other links). When extracting the energy consumption peak value, first lock the production period of 8:00-18:00 every day, and calculate the air conditioning energy consumption per hour: 8:00-9:00 energy consumption 95 kWh, 9:00-10:00 energy consumption 105 kWh, 10:00-11:00 energy consumption 110 kWh, 11:00-12:00 energy consumption 108 kWh……Through comparison of energy consumption values in each period, it is determined that the energy consumption peak value of 110 kWh in 10:00-11:00 is the energy consumption peak value of the process scene in the day. Considering the characteristics of short-time energy consumption surge in the injection molding heating stage, if the statistical period is adjusted to 15 minutes, the data collection granularity is further refined, and the instantaneous peak value of 115 kWh in the period of 10:30-10:45 may be captured. The specific statistical unit should be determined flexibly according to the process energy consumption fluctuation law, and the core target is to ensure that the extracted peak value can truly reflect the extreme value of energy consumption in this process scene.

[0049] The load fluctuation rate needs to consider the amplitude and frequency of energy consumption change in unit time. The amplitude reflects the "size" of energy consumption fluctuation, and the frequency reflects the "frequent degree" of energy consumption fluctuation. The combination of the two can quantify the energy consumption stability, which is an important part of energy consumption characteristic data. Still taking the plastic injection molding workshop as an example, when extracting the load fluctuation rate, first set the unit time to 30 minutes. Amplitude calculation: if the energy consumption rises from 90 kWh to 110 kWh in 30 minutes, the change amplitude is calculated according to the formula "(current energy consumption - previous period energy consumption) / previous period energy consumption", the result is (110-90) / 90≈22.2%; if it drops from 105 kWh to 100 kWh, the change amplitude is (105-100) / 105≈4.8%, the strength of single energy consumption fluctuation can be intuitively judged by the amplitude value. Frequency calculation: count the number of times the energy consumption changes more than 5% in 1 hour. If there are 3 significant fluctuations (30-minute amplitude 22.2%, 30-minute amplitude -8.1%, 30-minute amplitude 10.5%) in 1 hour, the fluctuation frequency is 3 times / hour, and the frequency value can reflect the intensity of energy consumption fluctuation. Comprehensive quantification: the load fluctuation rate adopts the calculation method of "average amplitude x frequency". In the above scenario, the average amplitude is (22.2%+4.8%+10.5%) / 3≈12.5%, and then multiplied by the fluctuation frequency of 3 times / hour, the load fluctuation rate is about 37.5% / hour. The higher the value, the more intense the air conditioning energy consumption fluctuation in this process scenario, and the worse the energy consumption stability.

[0050] The process-energy consumption matching difference value is obtained by comparing the deviation value of the actual energy consumption of the air conditioner and the theoretical energy consumption of the process requirement, which is a key indicator for measuring the adaptability of energy consumption and process requirement, and needs to be calculated in combination with the specific requirements of the plastic injection molding process. In the plastic injection molding workshop, when the process requires the mold temperature to be stable at 60℃, first calculate the theoretical energy consumption that meets the process requirement according to the air conditioner refrigeration efficiency (energy efficiency ratio 3.2), workshop heat loss coefficient (15 W / ℃), etc. through the heat load calculation formula "theoretical energy consumption=(mold target temperature-environmental benchmark temperature) x workshop heat loss coefficient / air conditioner energy efficiency ratio", the result is 90 kWh; if the actual collected air conditioner energy consumption is 110 kWh, the process-energy consumption matching difference value is calculated according to the formula "(actual energy consumption-theoretical energy consumption) / theoretical energy consumption", the result is (110-90) / 90≈22.2%; if the actual energy consumption is 85 kWh, the difference value is (85-90) / 90≈-5.6% (negative deviation represents that the energy consumption is lower than the theoretical value, further judgment is needed to determine whether the process requirement is met, to avoid excessive energy saving leading to process not meeting the standard). Through this indicator, the imbalance of energy consumption and process requirement matching can be clearly identified, providing direction for subsequent parameter optimization.

[0051] Through the above steps, the extraction of three energy consumption characteristic data of energy consumption peak (115 kWh / 15 minutes), load fluctuation rate (37.5% / hour), and process-energy consumption matching difference value (22.2%) is completed in the plastic injection molding process scene, forming a complete energy consumption characteristic data set, laying a foundation for subsequent division of energy consumption over-standard risk level and construction of multi-dimensional feature matrix.

[0052] Based on the numerical range of energy consumption peak, load fluctuation rate, and process-energy consumption matching difference value, the energy consumption over-standard risk level is divided, and risk level identification data is generated. Combined with industry energy consumption standards, enterprise energy saving targets and process requirements, for the three process scenes of "plastic injection molding", "mechanical processing" and "parts cleaning", the energy consumption peak, load fluctuation rate and process-energy consumption matching difference value are set with different threshold intervals to ensure that the threshold can accurately match the energy consumption law of each scene: for the energy consumption peak threshold (with 15 minutes as the statistical unit), the plastic injection molding workshop: low risk (≤100 kWh / 15 minutes), medium risk (101-120 kWh / 15 minutes), high risk (>120 kWh / 15 minutes). Mechanical processing workshop: low risk (≤90 kWh / 15 minutes), medium risk (91-110 kWh / 15 minutes), high risk (>110 kWh / 15 minutes). Parts cleaning workshop: low risk (≤80 kWh / 15 minutes), medium risk (81-100 kWh / 15 minutes), high risk (>100 kWh / 15 minutes).

[0053] For the load fluctuation rate threshold, the plastic injection molding workshop: low risk (≤20% / hour), medium risk (21-40% / hour), high risk (>40% / hour). Mechanical processing workshop: low risk (≤25% / hour), medium risk (26-35% / hour), high risk (>35% / hour). Parts cleaning workshop: low risk (≤30% / hour), medium risk (31-35% / hour), high risk (>35% / hour).

[0054] For the process-energy consumption matching difference value threshold, the plastic injection molding workshop: low risk (≤±10%), medium risk (±11-±25%), high risk (>±25%). Mechanical processing workshop: low risk (≤±15%), medium risk (±16-±30%), high risk (>±30%). Parts cleaning workshop: low risk (≤±15%), medium risk (±16-±30%), high risk (>±30%).

[0055] The risk level is divided by "weighted voting method", different weights are given to the three energy consumption characteristics (energy consumption peak weight 0.4, load fluctuation rate weight 0.3, process-energy consumption matching difference value weight 0.3), and the final level is determined according to the weight accumulation result of the risk level of each characteristic. Taking the energy consumption characteristic data (energy consumption peak 115 kWh / 15 minutes, load fluctuation rate 37.5% / hour, process-energy consumption matching difference value 22.2%) of the plastic injection molding workshop as an example, the energy consumption peak 115 kWh / 15 minutes belongs to medium risk, the weight contribution is 0.4x "medium risk" (marked as 2 points) =0.8 points; the load fluctuation rate 37.5% / hour belongs to medium risk, the weight contribution is 0.3x2 points=0.6 points; the process-energy consumption matching difference value 22.2% belongs to medium risk, the weight contribution is 0.3x2 points=0.6 points; the total weight score is 0.8+0.6+0.6=2 points, corresponding to the medium risk level, and the risk level identification data is generated as "plastic injection molding workshop-medium risk".

[0056] The process demand intensity, environmental interference coefficient and equipment energy efficiency attenuation information of the industrial process scene are collected, and a multi-dimensional feature matrix containing process demand intensity, environmental interference coefficient and equipment energy efficiency attenuation information is constructed. For the three core characteristic dimensions of process demand intensity, environmental interference coefficient and equipment energy efficiency attenuation information, a quantifiable rule is developed to ensure that the collected data can be directly used for matrix construction. Process demand intensity (quantization range 0-1): The higher the precision requirement (e.g. temperature control precision ±1℃ is better than ±3℃) and the longer the duration (e.g. 10 hours per day is better than 8 hours), the higher the intensity value. For example, the plastic injection molding workshop: the mold temperature needs to be stabilized at 60±1℃ (high precision), and lasts for 10 hours per day (long duration), and the process demand intensity is quantized as 0.9.

[0057] The temperature requirement of the mechanical processing workshop is 20±3℃ (medium precision), and lasts for 8 hours per day (medium duration), and the intensity is quantized as 0.6. The humidity requirement of the parts cleaning workshop is 60±8% (low precision), and lasts for 6 hours per day (short duration), and the intensity is quantized as 0.4. Environmental interference coefficient (quantization range 0-1): According to the actual intensity evaluation of the interference sources such as electromagnetic interference, dust and vibration in the industrial environment, the more the types of interference sources and the stronger the intensity, the higher the coefficient. For example, the plastic injection molding workshop: the injection molding machine generates strong electromagnetic interference, there is no significant dust but there is equipment vibration, and the environmental interference coefficient is quantized as 0.8. The mechanical processing workshop: the machine tool operation brings strong vibration, the electromagnetic interference is moderate, and there is no obvious dust, and the coefficient is quantized as 0.7; the parts cleaning workshop: only slight water flow noise exists, and there is no electromagnetic interference and dust, and the coefficient is quantized as 0.3.

[0058] Device energy efficiency attenuation information (quantization range 0-1): combined with the service life of air conditioning equipment and the frequency of maintenance, the energy efficiency attenuation rate is calculated, the longer the service life and the less timely the maintenance, the higher the attenuation rate (i.e. the larger the quantization value). The calculation formula can be simplified as: attenuation rate = (service life x 0.1) - (average annual maintenance times x 0.05), the result is truncated to the interval of 0-1. For example, a plastic injection molding workshop: the air conditioner has been used for 5 years, and the average annual maintenance is 2 times, the attenuation rate = (5 x 0.1) - (2 x 0.05) = 0.5 - 0.1 = 0.4. A mechanical processing workshop: the air conditioner has been used for 8 years, and the average annual maintenance is 1 time, the attenuation rate = (8 x 0.1) - (1 x 0.05) = 0.8 - 0.05 = 0.75; A parts cleaning workshop: the air conditioner has been used for 2 years, and the average annual maintenance is 4 times, the attenuation rate = (2 x 0.1) - (4 x 0.05) = 0.2 - 0.2 = 0.

[0059] The matrix adopts a row vector to represent different industrial process scenarios, and a column vector corresponds to "process demand intensity", "environmental interference coefficient" and "device energy efficiency attenuation information" respectively. Each element of the matrix is a specific quantization value of the feature. Combined with the feature data of the above three types of process scenarios, a multi-dimensional feature matrix is constructed as follows: row 1 (plastic injection molding workshop): [0.9, 0.8, 0.3]; row 2 (mechanical processing workshop): [0.6, 0.7, 0.6]; row 3 (parts cleaning workshop): [0.4, 0.3, 0.1]. This matrix clearly presents the differences of each feature in different scenarios, such as "high process demand intensity (0.9) + large environmental interference (0.8)" in the plastic injection molding workshop, "serious device energy efficiency attenuation (0.6)" in the mechanical processing workshop, which provides feature support for subsequent targeted development of energy-saving strategies. In addition, if the feature data of a newly added process scenario (such as an automobile painting workshop) is "process demand intensity 0.8, environmental interference coefficient 0.9, device energy efficiency attenuation information 0.2", it can be directly added as row 4 to the matrix, expanding the scenario coverage range of the matrix and providing complete feature data support for subsequent gradient boosting tree algorithm to select key factors.

[0060] S105, compare real-time energy consumption with historical same-period same-process data to identify abnormal signals of short-term energy consumption surge and load-energy consumption mismatch, and use energy consumption-process parameter correlation curve slope to generate energy consumption optimization dynamic correction factor.

[0061] In one embodiment, real-time energy consumption data of the industrial process is retrieved and compared with historical contemporaneous energy consumption data of the same process to establish a data comparison dimension. The real-time energy consumption data should focus on the current process operation cycle and include both instantaneous energy consumption and average energy consumption per unit time of the air conditioner during the current process operation cycle, reflecting short-term fluctuations and overall trends in energy consumption, respectively. Instantaneous energy consumption refers to the immediate energy consumption value of the air conditioner at a certain time, which should be captured through high-frequency acquisition to capture short-term fluctuations in energy consumption. Taking the textile printing and dyeing workshop fabric dyeing process as an example, the process runs from 9:00 to 17:00 every day (8-hour cycle), and the instantaneous energy consumption data is retrieved every 5 minutes through the air conditioner energy consumption monitoring terminal. The specific data is as follows: 9:00 is 120 kWh, 9:05 is 122 kWh, 9:10 is 118 kWh, and so on, and 17:00 is 115 kWh. These data can accurately present the instantaneous changes in energy consumption during the dyeing process (such as heating, temperature rising, and dyeing links), avoiding missing key fluctuation information due to long acquisition intervals. Average energy consumption per unit time refers to the average value of air conditioner energy consumption within a certain period, which should reflect the phased trend of energy consumption through period division. Still taking the dyeing process as an example, the period is divided into 1 hour units, and the average energy consumption of each period is calculated: in the 9:00-10:00 period, the average energy consumption is 119 kWh / h based on all instantaneous energy consumption data (12 data points) in the period; the average energy consumption of the 10:00-11:00 period is 121 kWh / h, and the difference in energy consumption of different dyeing stages (such as 10:00-11:00 for concentrated dyeing period, with slightly higher energy consumption than initial heating period) can be clearly identified through mean comparison, laying the foundation for subsequent comparison with historical data.

[0062] The historical contemporaneous data should match the two core conditions of "same season, same production load" to avoid the interference of seasonal environmental differences (such as higher cooling energy consumption in summer) and production load changes (such as order quantity changes leading to process time adjustment) on data comparison, and should include both mean and fluctuation range indicators. Still taking the textile printing and dyeing workshop dyeing process as an example, the energy consumption data under the same production load (5000 meters of dyed fabric per day, consistent with the current one) in the same period last year (such as May 2023) is retrieved. The energy consumption mean value is 118 kWh / h for the air conditioner energy consumption mean value of the dyeing process from 9:00 to 17:00 every day in May last year; the fluctuation range: the highest value of energy consumption in the same period last year is 125 kWh / h, the lowest value is 112 kWh / h, and the fluctuation interval is 112-125 kWh / h.

[0063] Based on the preset energy consumption difference threshold and load-energy matching benchmark, compare real-time energy consumption with historical same period and same process data to identify abnormal signals of short-term energy consumption surge and load-energy matching imbalance. Around the three core attributes of "instantaneous fluctuation-period average overall range" of energy consumption data, establish the two-way comparison dimension of real-time energy consumption and historical same period and same process data to ensure the comprehensiveness and pertinence of data comparison. For real-time instantaneous energy consumption vs. historical same period and same time period instantaneous energy consumption average: select the instantaneous energy consumption data in the current process operation period (such as 122 kWh at 9:05), and compare it with the instantaneous energy consumption average (117 kWh) of the same process, same time period (9:00-9:10) in the historical same period (such as May last year), focus on capturing the instantaneous abnormal fluctuation of short-term energy consumption, and avoid misjudgment caused by accidental single point data.

[0064] For real-time unit time average energy consumption vs. historical same period unit time average energy consumption: calculate the average energy consumption (119 kWh / h) of each period (such as 9:00-10:00) of the current process, and compare it with the average energy consumption (118 kWh / h) of the same process and the same period in the historical same period, analyze whether the stage trend of energy consumption deviates from the historical normal, and reflect whether the overall change of energy consumption is reasonable. For real-time energy consumption fluctuation range vs. historical same period energy consumption fluctuation range: calculate the maximum and minimum values (115-122 kWh) of energy consumption in the current process operation period, and compare them with the energy consumption fluctuation interval (112-125 kWh) of the same process in the historical same period, judge whether the overall stability of the current energy consumption conforms to the historical law, and investigate the abnormal risks caused by large-scale fluctuations.

[0065] Combined with the energy saving target of the enterprise and the requirement of the process on energy consumption stability, two types of core judgment criteria are developed to provide quantitative basis for abnormal identification. The energy consumption difference threshold includes the following information, short-term energy consumption surge threshold: for the rapid change of instantaneous energy consumption, set the energy consumption surge threshold within 10 minutes to 8%, that is, when the real-time energy consumption within 10 minutes increases by more than 8% compared with the previous time, it is determined as short-term energy consumption surge; period average deviation threshold: for the overall deviation of period average energy consumption, set the deviation threshold of real-time unit time average energy consumption from historical same period average to ±5%, and if it exceeds this range, it is considered as energy consumption average abnormality, which needs to be further investigated. The load-energy matching benchmark is as follows: based on the internal correlation between process load and energy consumption, set the correlation coefficient benchmark range. Taking the dyeing process of textile printing and dyeing workshop as an example, when the process load (cloth dyeing amount) increases by 10%, the air conditioning energy consumption should increase by 5%-7% synchronously, and this coefficient range is the load-energy matching benchmark; if the actual energy consumption increase exceeds or is lower than this range, it is determined as load-energy matching imbalance.

[0066] Identify short-term energy consumption surge anomaly signal, identify by monitoring the rise of real-time energy consumption per unit time (such as 10 minutes) whether it exceeds the preset threshold. The real-time instantaneous energy consumption of the textile printing and dyeing workshop at 9:10 is 118 kWh, and the instantaneous energy consumption rises to 128 kWh at 9:20, the rise in 10 minutes is calculated as (128-118) / 118≈8.47%, which exceeds the preset threshold of 8%, so it is determined as a "short-term energy consumption surge" anomaly signal; After investigation, the reason for the surge is that 1 heating equipment is added in the dyeing process, which causes the heat load of the workshop to rise sharply, and the air conditioner needs to increase the refrigeration power to maintain the required temperature and humidity of the process, and the subsequent targeted optimization of equipment operation scheme is needed.

[0067] Identify load-energy consumption matching imbalance anomaly signal, identify by comparing the correlation between actual energy consumption change and process load change with the preset benchmark. During the period of 10:00-11:00 of the textile printing and dyeing workshop, the process load (dyeing cloth quantity) increased by 10% (from 500 meters / hour to 550 meters / hour) compared with the previous period. According to the load-energy consumption matching benchmark, the air conditioner energy consumption should increase by 5%-7%. But the actual energy consumption increased from 119 kWh / h to 129 kWh / h, with an increase of (129-119) / 119≈8.4%, which exceeds the upper limit of 7%, so it is determined as a "load-energy consumption matching imbalance" anomaly signal; After checking, the imbalance reason is that the air conditioner fan is aging, and the fan needs to run at an excess rated power when the load increases, resulting in an energy consumption increase higher than the process load increase, so the fan needs to be maintained or replaced in time to restore the matching relationship.

[0068] Collect energy consumption data and process parameters corresponding to the industrial process, construct the energy consumption-process parameter correlation curve, calculate the slope of the curve at the current process parameter node, and use the slope to generate an energy consumption optimization dynamic correction factor. Collect energy consumption data and process parameters corresponding to the industrial process, for the dyeing process of the textile printing and dyeing workshop, preferentially select the core process parameter that has a significant impact on energy consumption, "dyeing temperature (℃)", through the energy consumption monitoring terminal and process parameter sensor, synchronously collect multiple sets of "dyeing temperature-air conditioner energy consumption" corresponding data, ensure that the data covers the commonly used parameter range of the process, the specific data is as follows: when the dyeing temperature is 60℃, the air conditioner energy consumption is 115 kWh / h. When the dyeing temperature is 65℃, the air conditioner energy consumption is 122 kWh / h. When the dyeing temperature is 70℃, the air conditioner energy consumption is 130 kWh / h. When the dyeing temperature is 75℃, the air conditioner energy consumption is 138 kWh / h.

[0069] The collected core process parameter "dyeing temperature" is taken as the X axis, and the corresponding air conditioning energy consumption is taken as the Y axis. The above multiple data points are introduced into a data analysis tool (such as Excel, Matlab) for fitting to generate a line energy consumption-process parameter correlation curve. Through linear regression calculation, the curve equation is y = 1.4x + 21 (where x is the dyeing temperature and y is the air conditioning energy consumption). From the curve trend, the correlation law that "the air conditioning energy consumption increases by about 7 kWh / h for every 5℃ increase in dyeing temperature" can be observed intuitively. The curve accurately reflects the internal relationship between the change of dyeing temperature and the change of energy consumption, laying a foundation for subsequent slope calculation.

[0070] The slope of the curve at the current process parameter node is calculated, and the slope of the energy consumption-process parameter correlation curve directly reflects the influence of the change of the process parameter on the energy consumption. The greater the slope, the more sensitive the energy consumption is to the change of the process parameter. For the linear curve y = 1.4x + 21 constructed this time, the slope is a constant value of 1.4. If the constructed curve is a nonlinear curve (such as a quadratic function y = ax² + bx + c), the tangent slope of the current process parameter node needs to be calculated through the derivative formula to reflect the instantaneous influence of the change of the parameter at this node on the energy consumption. Assuming that the actual running parameter of the current dyeing process is "dyeing temperature 70℃", the slope of the curve at the node is 1.4, which means that under the current process state, for every 1℃ change in dyeing temperature, the air conditioning energy consumption will change in the same direction by 1.4 kWh / h (such as an increase of 1.4 kWh / h for every 1℃ increase in temperature, and a decrease of 1.4 kWh / h for every 1℃ decrease in temperature).

[0071] The slope is used to generate an energy consumption optimization dynamic correction factor. The calculation of the correction factor needs to combine the slope, the preset energy consumption optimization target and the adjustable range of process parameters to ensure that the correction scheme meets the energy saving demand and does not violate the process constraints. The calculation formula is: correction factor=(target energy consumption reduction range×current energy consumption) / (slope×adjustable range of process parameters). Taking the current scene of a textile printing and dyeing workshop as an example, the target energy consumption reduction range is set to 5% in combination with the enterprise energy saving target; the air conditioning energy consumption corresponding to the current dyeing temperature of 70℃ is 130kWh / h; the slope is 1.4 (calculated). Because the dyeing process requires the temperature to be stable at 67-73℃, the adjustable range of dyeing temperature is ±3℃. Substitute the above parameters into the formula to calculate: correction factor=(5%×130) / (1.4×3)≈6.5 / 4.2≈1.55. The actual meaning of this correction factor is that if a 5% energy consumption reduction range (i.e. energy consumption is reduced from 130kWh / h to 123.5kWh / h) is required, at the current dyeing temperature of 70℃, the dyeing temperature can be reduced by about 1.55℃ (within the adjustable range of ±3℃), combined with the synchronous adjustment of the air conditioning fan parameters, to achieve the energy consumption optimization target. At the same time, the correction factor has the dynamic updating feature - if the process parameters change later (such as the dyeing temperature rises to 75℃ and the current energy consumption becomes 138kWh / h), a new correction factor can be calculated by substituting the formula to ensure that it always adapts to the real-time process state.

[0072] S106, combined with the production scale, process complexity and equipment configuration of industrial enterprises, the users are grouped, the gradient boosting tree algorithm is used to screen the key influence factors of the multi-dimensional feature matrix and the energy consumption optimization dynamic correction factor, and the individualized energy saving control model is constructed by fusing the energy consumption optimization parameters, process constraints and equipment operation limit information.

[0073] In one embodiment, a quantifiable grouping basis is established from the three core dimensions of "production scale-process complexity-equipment configuration" to avoid bias caused by subjective division. Production scale: taking enterprise daily industrial output value (ten thousand yuan) as the quantitative indicator, divided into small scale (daily output value ≤50 thousand yuan), medium scale (50 thousand yuan < daily output value ≤200 thousand yuan), large scale (daily output value >200 thousand yuan); Process complexity: according to the number of process links (such as raw material pretreatment, processing, detection, etc. Independent links) and parameter control accuracy (such as temperature control accuracy ±1℃ for high, ±3℃ for medium, ±5℃ for low) comprehensive score (full score 10 points), divided into low complexity (score ≤4 points), medium complexity (4 points < score ≤7 points), high complexity (score >7 points); Equipment configuration: based on the number of modules (such as the total number of independent modules such as compressors, fans, humidifiers, etc.) and the service life of the equipment (annual attenuation rate <5% for new, 5%-10% for medium, >10% for old) as the basis, divided into basic configuration (module number ≤5 and equipment service life >10%), standard configuration (5 < module number ≤10 and 5% ≤ equipment service life ≤10%), high-end configuration (module number >10 and equipment service life <5%).

[0074] Take four enterprises in the mechanical manufacturing industry as an example, complete grouping combined with the above dimensions: Enterprise A: daily output value 30 thousand yuan (small scale), process links 3 and temperature control accuracy ±5℃ (score 3 points, low complexity), air conditioning module 4 and equipment service life 12% (basic configuration) → grouped into "small scale-low complexity-basic configuration group"; Enterprise B: daily output value 120 thousand yuan (medium scale), process links 5 and temperature control accuracy ±3℃ (score 6 points, medium complexity), air conditioning module 8 and equipment service life 8% (standard configuration) → grouped into "medium scale-medium complexity-standard configuration group"; Enterprise C: daily output value 280 thousand yuan (large scale), process links 8 and temperature control accuracy ±1℃ (score 9 points, high complexity), air conditioning module 15 and equipment service life 3% (high-end configuration) → grouped into "large scale-high complexity-high-end configuration group"; Enterprise D: daily output value 60 thousand yuan (medium scale), process links 4 and temperature control accuracy ±3℃ (score 5 points, medium complexity), air conditioning module 6 and equipment service life 7% (standard configuration) → same group as Enterprise B, grouped into "medium scale-medium complexity-standard configuration group".

[0075] Gradient boosting tree algorithm generates multiple decision trees by iteration, accumulates the prediction results of each tree, quantifies the influence weight of each feature on energy consumption optimization, and filters out core factors to reduce redundant feature interference and improve the accuracy and operation efficiency of subsequent models. Taking the "medium-scale-medium complexity-standard configuration group" (such as enterprises B and D) as an example, the input feature set includes two types of data, a multi-dimensional feature matrix: the row vector of the matrix is the enterprise process scene (such as mechanical processing, part cleaning), and the column vector is the process demand intensity (quantized as 0-1), the environmental interference coefficient (quantized as 0-1), and the equipment energy efficiency decay information (quantized as 0-1), such as the feature vector of the mechanical processing scene of enterprise B is [0.7, 0.6, 0.5]; the energy consumption optimization dynamic correction factor: the correction factor calculated based on the slope of the energy consumption-process parameter correlation curve of the group of enterprises, such as the correction factor of the mechanical processing scene of enterprise B is 1.2, and the correction factor of the part cleaning scene is 0.8.

[0076] Initialize the model: take the mean of all input features as the initial prediction value, and calculate the initial residual error (the difference between the actual energy consumption optimization effect and the initial prediction value); generate decision trees by iteration: build a decision tree to fit the residual error in each iteration, such as the first round of tree finds that "process demand intensity > 0.6" significantly reduces the residual error, and the second round of tree captures the influence of "equipment energy efficiency decay information > 0.4" on the residual error, and generates 100 decision trees (the number of trees can be adjusted according to the amount of data) by iteration; calculate the importance of features: calculate the importance score by the contribution of features to node splitting in all decision trees (such as the reduction of Gini coefficient), and the higher the score, the greater the influence on energy consumption optimization.

[0077] For the "medium-scale-medium complexity-standard configuration group", the top 3 key factors with the highest importance scores are selected: process demand intensity: score 0.35 (core influencing factor, the higher the process demand, the more the air conditioner needs to meet the process requirements, and the stronger the constraint on energy consumption optimization); equipment energy efficiency decay information: score 0.28 (the more serious the equipment decay, the smaller the energy consumption optimization space, and the more targeted parameters need to be adjusted to balance energy efficiency and process demand); energy consumption optimization dynamic correction factor: score 0.22 (directly reflects the potential of energy consumption optimization under current process parameters, the larger the correction factor, the more significant the optimization space). The "environmental interference coefficient" has a score of only 0.15, and it is determined as a non-key factor and is excluded because the environmental interference in the workshop of this group of enterprises is relatively stable (such as small fluctuations in electromagnetic interference in the mechanical processing workshop).

[0078] With the selected key factors as the core, integrate three types of key information, establish the "factor-parameter-constraint" association logic, build a personalized model that adapts to a specific user group, and ensure that the model meets both the energy-saving goal and the actual limitations of the process and equipment. Take the "medium-scale-medium-complexity-standard-configuration-group" machining scene as an example: Energy optimization parameters: Based on key factors to determine optimization target parameters, such as target energy consumption threshold (110 kWh / h), energy consumption reduction target (5%), determined by "process demand intensity" and "correction factor", the demand intensity is high, and the reduction target is appropriately relaxed;

[0079] Process constraints: Hard requirements of the process on the environment, such as the workshop temperature needs to be stable at 20±2℃, relative humidity 50±5%, exceeding which will affect the processing precision, the constraint strictness is directly determined by "process demand intensity"; Equipment running limit information: Physical running boundaries of air conditioning equipment, such as compressor frequency upper limit 60Hz, lower limit 30Hz, fan speed upper limit 1800r / min, lower limit 800r / min, corrected by "equipment energy efficiency decay information", and the upper limit is appropriately lowered when the decay is severe (such as old equipment compressor upper limit set to 55Hz).

[0080] With "minimizing energy consumption" as the objective function, and process constraints and equipment limits as boundary conditions, establish the correlation equation between key factors and air conditioning operation parameters: Objective function: Energy consumption = 0.35 × Process demand intensity × Compressor frequency + 0.28 × Equipment energy efficiency decay information × Fan speed - 0.22 × Correction factor × Humidification amount (coefficient based on characteristic importance score adjustment), the goal is to make energy consumption ≤110 kWh / h; Constraint conditions: 20℃ ≤ Workshop temperature ≤22℃ (corresponding to compressor frequency 35-55Hz), 45%RH ≤ Relative humidity ≤55% (corresponding to humidification amount 2-4kg / h), 30Hz ≤ Compressor frequency ≤55Hz, 800r / min ≤ Fan speed ≤1800r / min; Parameter solving: Solve the equation by gradient descent algorithm to get the optimal air conditioning operation parameters that meet the constraints, such as when the process demand intensity is 0.7, the equipment energy efficiency decay is 0.5, and the correction factor is 1.2, the optimal parameters are compressor frequency 45Hz, fan speed 1200r / min, and humidification amount 3kg / h, at this time the energy consumption is about 108kWh / h, meeting the target and constraints.

[0081] The model parameters of different user groups are different, such as "large-scale-high complexity-high-end configuration group" (enterprise C): the key factors are "process demand intensity (0.4), correction factor (0.3), and equipment energy efficiency decay (0.2)" (due to the new equipment, the decay effect is reduced); the process constraint is more strict (temperature 20±1℃), and the equipment limit is higher (compressor frequency upper limit 65Hz); the objective function is adjusted to energy consumption=0.4×process demand intensity×compressor frequency+0.3×correction factor×fan speed-0.2×equipment energy efficiency decay×fresh air volume, to realize personalized adaptation.

[0082] In S107, the target operation parameter output based on the personalized energy-saving control model is combined with the time correlation information of the industrial process time sequence arrangement and the air conditioning equipment operation characteristics to generate real-time dynamic adjustment instructions and time-division energy-saving control strategies.

[0083] In an embodiment, the target operation parameters output by the personalized energy-saving control model are extracted, and the industrial process time sequence arrangement and the air conditioning equipment operation characteristics are collected to establish a time correlation mapping relationship among the three, and parameter-time sequence-equipment correlation data is generated. To generate parameter-time sequence-equipment correlation data, the target operation parameters output by the personalized energy-saving control model need to be extracted first. This model will output adapted air conditioning operation parameters according to the characteristics of different user groups, and the parameters need to cover the core regulation dimensions of air conditioning to ensure that the process demand and energy-saving goals can be met. Taking the "medium-scale-medium complexity-standard configuration group" machining workshop as an example, the target operation parameters extracted from the model include: compressor frequency 45Hz (to maintain workshop temperature 20±2℃), fan speed 1200r / min (to ensure air circulation efficiency), humidification amount 3kg / h (to control relative humidity 50±5%), and fresh air volume 200m³ / h (to balance indoor air quality and energy consumption).

[0084] After extracting the target operation parameters, the industrial process time sequence arrangement and the air conditioning equipment operation characteristics need to be collected. Specifically, for the industrial process time sequence arrangement: the time nodes, duration, and corresponding demand intensity of each process link in the machining workshop are determined, specifically: 8:00-10:00 (engine cylinder rough machining, process demand intensity 0.9, temperature needs to be strictly controlled), 10:00-12:00 (part semi-finishing machining, demand intensity 0.7), 13:00-15:00 (precision detection, demand intensity 0.8, higher temperature control accuracy is required), and 15:00-17:00 (finished product assembly, demand intensity 0.5). For the air conditioning equipment operation characteristics: the operation performance of the equipment under different parameters at different times is recorded, such as 8:00-10:00 (peak period of power grid load) compressor frequency exceeding 50Hz is prone to voltage fluctuation, and 15:00-17:00 (environmental temperature is relatively low) fan speed below 1000r / min can still meet the air circulation demand.

[0085] Finally, the time correlation mapping relationship of the three is established to generate parameter-time sequence-equipment correlation data. The target operating parameter is associated with the process time sequence and equipment characteristics of the corresponding period one by one to form the correlation data of each period. For example, 8:00-10:00 (cylinder rough machining): the correlation data is "compressor frequency 45 Hz + process demand intensity 0.9 + equipment power grid peak period frequency ≤ 50 Hz"; 15:00-17:00 (finished product assembly): the correlation data is "fan speed 1200 r / min + process demand intensity 0.5 + equipment speed can be reduced to 1000 r / min under low ambient temperature"; the association of all periods is completed in turn, and finally the complete parameter-time sequence-equipment correlation data sequence is generated, clearly presenting the adaptation relationship of the three at different time nodes.

[0086] Based on the parameter-time sequence-equipment correlation data, for the real-time running state of the industrial process, the deviation value of the target operating parameter and the actual operating parameter is calculated in real time, and the real-time dynamic adjustment instruction is generated combining the real-time running characteristics of the air conditioning equipment, wherein the real-time dynamic adjustment instruction includes parameter adjustment direction, adjustment amplitude and execution time limit, and the instruction generation frequency is synchronized with the process state change frequency.

[0087] The industrial process time sequence arrangement and the air conditioning equipment running characteristics are determined, which lays a foundation for subsequent correlation data construction. For the industrial process time sequence arrangement, the time nodes, duration and corresponding demand intensity of each process link are determined. Taking a mechanical processing workshop as an example, the time sequence arrangement is 8:00-10:00 (engine cylinder rough machining, process demand intensity 0.9, strict temperature control is required), 10:00-12:00 (semi-precision machining of parts, demand intensity 0.7), 13:00-15:00 (precision detection, demand intensity 0.8, higher temperature control accuracy is required), 15:00-17:00 (finished product assembly, demand intensity 0.5). For the running characteristics of the air conditioning equipment, the running performance of the equipment under different parameters at different periods needs to be recorded, such as the air conditioner in the workshop, which is prone to voltage fluctuation when the compressor frequency exceeds 50 Hz during 8:00-10:00 (peak period of power grid load), and the fan speed can still meet the air circulation demand when it is lower than 1000 r / min during 15:00-17:00 (low ambient temperature).

[0088] Then, the "target operating parameters-process timing-equipment characteristics" are correspondingly associated with time as the link to form the parameter-timing-equipment association data for each time period. 8:00-10:00 (rough machining of cylinder body): the association data is "compressor frequency 45 Hz + process demand intensity 0.9 + equipment grid peak period frequency ≤ 50 Hz". 10:00-12:00 (semi-finishing of parts): the association data is "compressor frequency 43 Hz + process demand intensity 0.7 + equipment regular period frequency can be adjusted within 40-50 Hz". 13:00-15:00 (precision detection): the association data is "compressor frequency 46 Hz + process demand intensity 0.8 + equipment grid flat peak period frequency can be adjusted within 42-52 Hz". 15:00-17:00 (finished product assembly): the association data is "fan speed 1200 r / min + process demand intensity 0.5 + equipment speed can be reduced to 1000 r / min under low ambient temperature"; the association of all time periods is completed in turn, and finally the complete parameter-timing-equipment association data sequence is generated, clearly presenting the adaptation relationship of the three at different time nodes.

[0089] Subsequently, based on the parameter-timing-equipment association data, for the real-time running state of the industrial process, the real-time dynamic adjustment instructions are generated by real-time calculation of the deviation value of the target operating parameters and the actual operating parameters, combined with the real-time running characteristics of the air conditioning equipment. For real-time calculation of the deviation value: taking the running data of the mechanical processing workshop at 8:30 (corresponding to the 8:00-10:00 period, the target compressor frequency in the association data is 45 Hz) as an example, the actual value of the core operating parameters of the air conditioner is collected in real time and compared with the target value, and it is calculated that: the target compressor frequency is 45 Hz, the actual frequency is 48 Hz, the deviation value is +3 Hz (the actual value is higher than the target value); the target relative humidity is 50%, the actual humidity is 55%, the deviation value is +5% RH (the actual value is higher than the target value); the target fresh air volume is 200 m³ / h, the actual fresh air volume is 190 m³ / h, the deviation value is -10 m³ / h (the actual value is lower than the target value); combined with the equipment characteristics to judge the correction feasibility: referring to the air conditioning equipment running characteristics in the parameter-timing-equipment association data (8:00-10:00 grid load peak period compressor frequency ≤ 50 Hz), it is judged whether the deviation can be corrected by adjusting and the correction safety range-the actual frequency of the compressor is 48 Hz, which is higher than the target 45 Hz, but does not exceed the limit of 50 Hz, which can be adjusted by reducing the frequency; the actual humidity is 55%, the equipment humidification module is currently running normally, which can be corrected by reducing the humidification amount; the actual fresh air volume is 190 m³ / h, the equipment fresh air valve has no fault, which can increase the valve opening to increase the fresh air volume;

[0090] The real-time dynamic adjustment instruction is generated, specifically, the real-time dynamic adjustment instruction contains parameter adjustment direction, adjustment amplitude and execution time limit, and the instruction generation frequency is kept synchronous with the process state change frequency (for example, the process fluctuates once every 10 minutes, and the instruction is generated once every 10 minutes). For the above deviation, the generated adjustment instruction is: “compressor frequency: from 48Hz to 45Hz, adjustment direction is reduced, adjustment amplitude -3Hz, execution time limit is within 5 minutes, to avoid temperature fluctuation caused by sudden frequency drop”; “humidification amount: from 3kg / h to 2kg / h, adjustment direction is reduced, adjustment amplitude -1kg / h, execution time limit is within 3 minutes, to ensure that the humidity gradually decreases to 50%”; “fresh air volume: from 190m³ / h to 200m³ / h, adjustment direction is increased, adjustment amplitude +10m³ / h, execution time limit is within 2 minutes, to avoid sudden change of fresh air volume affecting indoor temperature”.

[0091] To generate time period energy saving control strategy, first of all, according to the time period division in industrial process time sequence arrangement, the process requirements in different time periods are determined, and then combined with the process requirement intensity corresponding to each time period and the running characteristic difference of air conditioning equipment in different time periods, the target running parameter is optimized, and finally the core control rule of each time period is determined. Specifically, taking a machining workshop as an example: first, sort out the industrial process time sequence arrangement of the machining workshop, divide the production cycle of one day into multiple core time periods according to the difference of process requirements, and determine the corresponding process content and requirement intensity of each time period. High demand period: 8:00-10:00 (engine cylinder rough machining, process requirement intensity 0.9, strict temperature control is required to ensure machining precision), 13:00-15:00 (precision detection, process requirement intensity 0.8, higher temperature control accuracy requirement). Medium demand period: 10:00-12:00 (part semi-finishing machining, process requirement intensity 0.7, temperature and humidity requirement is more relaxed than rough machining). Low demand period: 15:00-17:00 (finished product assembly, process requirement intensity 0.5, no strict accuracy requirement for temperature and humidity).

[0092] The target operating parameters of each period are adjusted according to the process demand intensity and equipment characteristics. For the core period, the process demand intensity and air conditioning equipment operating characteristics of each period are analyzed, and the target operating parameters of each period are adjusted. High demand period (8:00-10:00): process demand intensity 0.9 (high temperature control demand), air conditioning equipment in the peak period of power grid load (compressor frequency more than 50Hz easy to appear voltage fluctuation), so the target compressor frequency is adjusted from the basic value 45Hz to 46Hz (ensure the temperature is stable at 20±2℃), the fresh air volume is maintained at 200m³ / h to balance the air quality, at the same time, the compressor frequency is limited not to exceed 50Hz, to avoid the influence of power grid fluctuation on equipment operation. Medium demand period (10:00-12:00): process demand intensity 0.7, air conditioning equipment in the flat peak period of power grid (frequency regulation space is larger), the target compressor frequency is adjusted to 43Hz, the fan speed is maintained at 1200r / min, and the humidification amount is 2.5kg / h, which meets the process demand while reducing energy consumption. Low demand period (15:00-17:00): process demand intensity 0.5, low ambient temperature (air humidity is easy to maintain), air conditioning equipment fan can still meet the air circulation demand at low speed, so the target fan speed is reduced from 1200r / min to 1000r / min, and the humidification amount is reduced from 3kg / h to 1kg / h, reducing unnecessary energy consumption.

[0093] The time-sharing energy-saving control strategy needs to clarify the core operating parameter range of air conditioning, module start-stop rule and energy consumption control benchmark of each period to ensure that the strategy can be implemented. For 8:00-10:00 (high demand): the core parameter range is compressor frequency 45-50Hz, fan speed 1200-1300r / min, and humidification amount 2-3kg / h; the module start-stop rule is that the compressor, fan and humidification module run all the time without intermittent shutdown; the energy consumption control benchmark is ≤110kWh / h. For 10:00-12:00 (medium demand): the core parameter range is compressor frequency 40-45Hz, fan speed 1100-1200r / min, and humidification amount 2-2.5kg / h; the module start-stop rule is that the compressor and fan run all the time, and the humidification module starts and stops every 30 minutes (flexibly adjusted according to the humidity monitoring value); the energy consumption control benchmark is ≤100kWh / h.

[0094] For 13:00-15:00 (high demand): the core parameter range is consistent with that of 8:00-10:00 (compressor frequency 45-50 Hz, fan speed 1200-1300 r / min, humidification amount 2-3 kg / h); the module start-stop rule is that the compressor, fan and humidification module are all running; and the energy consumption control benchmark is ≤110 kWh / h. For 15:00-17:00 (low demand): the core parameter range is compressor frequency 40-45 Hz, fan speed 1000-1100 r / min, and humidification amount 1-2 kg / h; the module start-stop rule is that the compressor and fan are all running, and the humidification module is started and stopped as needed (started when the workshop humidity is <45%, and stopped when the humidity reaches 50%); and the energy consumption control benchmark is ≤90 kWh / h. Through the above steps, a complete time period energy saving control strategy covering the whole production cycle is formed, which not only ensures that the process requirements in each period are met, but also optimizes energy consumption according to the characteristics of the equipment and the demand intensity, so as to achieve the customized energy saving goal.

[0095] In an embodiment, as shown in Figure 2 The application also provides a customized energy-saving air conditioning control device for industrial process requirements, comprising:

[0096] The acquisition module 201 is configured to acquire real-time process parameters, environmental data and air conditioning operation history energy consumption archives of industrial production, remove industrial environmental electromagnetic interference and equipment vibration noise by using a Kalman filtering algorithm, and generate a standardized process-environment-energy consumption correlation data sequence.

[0097] The processing module 202 is used for converting the standardized process-environment-energy consumption correlation data sequence into a three-dimensional process load distribution atlas, and after processing by a fluid dynamics simulation software, a self-adaptive grid division algorithm is selected to subdivide the high-load process area, and an individualized air conditioner dynamic load prediction model is constructed in combination with the differences in thermal and humid characteristics of different industrial scenes; based on the individualized air conditioner dynamic load prediction model, a priority factor of different industrial processes is extracted to construct a dynamic parameter adjustment matrix, and a parallel calculation is performed on the air conditioner multi-module operation state to obtain an air conditioner operation parameter combination under a target energy consumption; according to the industrial process scene, an energy consumption peak value, a load fluctuation rate, a process-energy consumption matching difference value, a risk level of energy consumption exceeding the standard, a multi-dimensional feature matrix containing process demand intensity, environmental interference coefficient and equipment energy efficiency attenuation information are extracted, and an energy consumption optimization dynamic correction factor is generated by using the slope of the energy consumption-process parameter correlation curve; the users are grouped in combination with the production scale, process complexity and equipment configuration of the industrial enterprise, the gradient boosting tree algorithm is used to screen the key influence factors of the multi-dimensional feature matrix and the energy consumption optimization dynamic correction factor, the energy consumption optimization parameters, the process constraint conditions and the equipment operation limit information are fused to construct a personalized energy-saving control model; based on the target operation parameter output of the personalized energy-saving control model, in combination with the time correlation information of the industrial process time sequence arrangement and the air conditioner equipment operation characteristics, real-time dynamic adjustment instructions and time-sharing energy-saving control strategies are generated.

[0098] The computer readable storage medium provided by the above embodiments of the application has the same beneficial effects as the method adopted, run or implemented by the application program stored therein.

[0099] Each of the embodiments in the present application is described in a related manner, and the same or similar parts between the embodiments can be referred to. Each embodiment focuses on the difference from other embodiments. In particular, the evaluation of the customized energy-saving air conditioner control method, the electronic device, the electronic equipment, and the readable storage medium embodiments are basically similar to the above-mentioned customized energy-saving air conditioner control method embodiments, so the description is relatively simple, and the relevant parts can be referred to the above-mentioned customized energy-saving air conditioner control method embodiments.

Claims

1. A customized energy-saving air conditioning control method for industrial process needs, characterized in that, include: The system acquires real-time process parameters, environmental data, and historical energy consumption records of air conditioning operation in industrial production. It then uses a Kalman filter algorithm to remove electromagnetic interference and equipment vibration noise from the industrial environment, generating a standardized process-environment-energy consumption correlation data sequence. After converting the standardized process-environment-energy consumption correlation data sequence into a three-dimensional process load distribution map, it is processed by fluid dynamics simulation software. An adaptive mesh generation algorithm is selected to subdivide the high-load process area. Combined with the differences in thermal and humidity characteristics of different industrial scenarios, an individualized air conditioning dynamic load prediction model is constructed. Based on the individualized air conditioning dynamic load prediction model, priority factors of different industrial processes are extracted to construct a dynamic parameter adjustment matrix. Parallel calculations are performed on the operating status of multiple air conditioning modules to obtain the combination of air conditioning operating parameters under the target energy consumption. Based on industrial process scenarios, peak energy consumption, load fluctuation rate, and process-energy consumption matching difference values ​​are extracted to classify the risk level of energy consumption exceeding standards, and a multi-dimensional feature matrix containing information on process demand intensity, environmental interference coefficient, and equipment energy efficiency degradation is constructed. By comparing real-time energy consumption with historical data of the same process, abnormal signals such as short-term energy consumption surges and load-energy consumption mismatch are identified, and dynamic correction factors for energy consumption optimization are generated using the slope of the energy consumption-process parameter correlation curve. Users are grouped based on the production scale, process complexity, and equipment configuration of industrial enterprises. The gradient boosting tree algorithm is used to screen key influencing factors of multidimensional feature matrix and dynamic correction factor for energy consumption optimization. Personalized energy-saving control model is constructed by integrating energy consumption optimization parameters, process constraints, and equipment operating limit information. Based on the target operating parameter output of the personalized energy-saving control model, and combined with the time correlation information of industrial process timing and air conditioning equipment operating characteristics, real-time dynamic adjustment instructions and time-sharing energy-saving control strategies are generated.

2. The method as described in claim 1, characterized in that, After converting the standardized process-environment-energy consumption correlation data sequence into a three-dimensional process load distribution map, it is processed by fluid dynamics simulation software. An adaptive mesh generation algorithm is used to subdivide the high-load process area. Combined with the differences in thermal and humidity characteristics of different industrial scenarios, an individualized dynamic air conditioning load prediction model is constructed, including: The standardized process-environment-energy consumption correlation data sequence is converted into a three-dimensional process load distribution map to generate basic load visualization data. The three-dimensional process load distribution map constructs a multi-dimensional correlation visualization map by mapping process parameters to the X-axis, environmental data to the Y-axis, and energy consumption data to the Z-axis. The three-dimensional process load distribution map is imported into the fluid dynamics simulation software for simulation calculation to generate thermal and moisture load field simulation data. The fluid dynamics simulation software simulates the air flow trajectory and heat and moisture exchange efficiency in the industrial space, and quantifies the thermal and moisture load intensity of different process areas. An adaptive mesh generation algorithm is used to subdivide the high-load process area in the thermal and humidity load field simulation data to generate differentiated mesh data. The adaptive mesh generation algorithm identifies the thermal and humidity load density in real time. When the load density exceeds a preset threshold, it automatically triggers mesh refinement. High-density meshes are used for high-load areas and low-density meshes are used for low-load areas. Collect parameters showing differences in thermal and humidity characteristics in different industrial scenarios, construct a scenario-based thermal and humidity characteristic constraint library, and generate scenario constraint data. The scenario-based thermal and humidity characteristic constraint library customizes parameters to meet the unique thermal and humidity requirements of different scenarios. By integrating differentiated grid data with scenario-constrained data, an individualized dynamic load prediction model for air conditioning is constructed.

3. The method as described in claim 1, characterized in that, Based on an individualized dynamic load prediction model for air conditioning, priority factors for different industrial processes are extracted to construct a dynamic parameter adjustment matrix. Parallel calculations are then performed on the operating states of multiple air conditioning modules to obtain the combination of air conditioning operating parameters under the target energy consumption, including: Based on the individualized air conditioning dynamic load prediction model, priority factors of different industrial processes are extracted, and a dynamic parameter adjustment matrix is ​​constructed. The priority factor extraction takes the production criticality, heat and humidity demand urgency, and energy consumption sensitivity of the industrial process as the core dimensions. The dynamic parameter adjustment matrix associates and maps the priority factors of each process with the air conditioning adjustment parameters to generate a parameter adjustment logic framework that can be updated in real time. The dynamic parameter adjustment matrix is ​​input into the parallel computing module to synchronously calculate the operating status of multiple air conditioning modules and generate multiple sets of candidate operating parameters. The parallel computing module adopts a distributed computing architecture and performs parameter iterative calculations simultaneously, taking into account the independent operating characteristics and interactive influence relationships of each air conditioning module. Based on the preset target energy consumption threshold, the candidate operating parameter set is screened and optimized to obtain the air conditioning operating parameter combination under the target energy consumption. The screening process involves constructing a dual-objective evaluation function for energy consumption and process satisfaction, introducing parameter sensitivity analysis, and predicting the energy consumption impact of small fluctuations in key adjustment parameters.

4. The method as described in claim 1, characterized in that, Energy consumption peaks, load fluctuation rates, and process-energy consumption matching differences are extracted based on industrial process scenarios to classify energy consumption exceedance risk levels. A multi-dimensional feature matrix is ​​constructed, including information on process demand intensity, environmental interference coefficients, and equipment energy efficiency degradation. Energy consumption peak, load fluctuation rate, and process-energy consumption matching difference value are extracted according to industrial process scenarios to generate energy consumption feature data. Among them, the energy consumption peak is extracted as the maximum value of air conditioning energy consumption per unit time under the corresponding process scenario, the load fluctuation rate is calculated as the amplitude and frequency of energy consumption change per unit time, and the process-energy consumption matching difference value is obtained by comparing the deviation value between actual energy consumption and theoretical energy consumption required by the process. Based on the numerical range of peak energy consumption, load fluctuation rate, and process-energy consumption matching difference, the risk level of energy consumption exceeding the standard is divided, and risk level identification data is generated. Among them, multiple sets of energy consumption feature threshold ranges are preset, and the extracted energy consumption feature data is compared with the threshold ranges to automatically match the corresponding risk level. Information on process demand intensity, environmental interference coefficient, and equipment energy efficiency degradation in industrial process scenarios is collected. A multi-dimensional feature matrix containing information on process demand intensity, environmental interference coefficient, and equipment energy efficiency degradation is constructed. The multi-dimensional feature matrix uses row vectors to represent different industrial process scenarios, and column vectors to correspond to the feature dimensions of process demand intensity, environmental interference coefficient, and equipment energy efficiency degradation information, respectively. Each matrix element is a specific quantitative value of the feature.

5. The method as described in claim 1, characterized in that, By comparing real-time energy consumption with historical data from the same period and process, abnormal signals such as short-term energy consumption spikes and load-energy consumption imbalances are identified. Dynamic correction factors for energy consumption optimization are generated using the slope of the energy consumption-process parameter correlation curve, including: Retrieve real-time energy consumption data of industrial processes and historical energy consumption data of the same process in the same period to establish data comparison dimensions. Among them, real-time energy consumption data is the instantaneous energy consumption and average energy consumption per unit time of air conditioning in the current process operation cycle, and historical energy consumption data of the same process in the same period is the average energy consumption and fluctuation range under the same season and the same production load in the past. Based on preset energy consumption difference thresholds and load-energy consumption matching benchmarks, real-time energy consumption is compared with historical data of the same process in the same period to identify abnormal signals such as short-term energy consumption surges and load-energy consumption imbalances. Short-term energy consumption surges are determined by monitoring whether the energy consumption increase per unit time exceeds the threshold, and load-energy consumption imbalances are determined by comparing whether the correlation between actual energy consumption changes and process load changes meets the benchmark. Collect energy consumption data and process parameters for the corresponding industrial process, construct an energy consumption-process parameter correlation curve, calculate the slope of the curve at the current process parameter node, and use this slope to generate a dynamic correction factor for energy consumption optimization.

6. The method as described in claim 5, characterized in that, Based on the target operating parameter output of the personalized energy-saving control model, and combined with the time correlation information between the industrial process sequence and the operating characteristics of the air conditioning equipment, real-time dynamic adjustment commands and time-sharing energy-saving control strategies are generated, including: Extract the target operating parameters output by the personalized energy-saving control model, and simultaneously collect the industrial process timing and air conditioning equipment operating characteristics to establish a time-related mapping relationship among the three, generating parameter-time-equipment related data. Based on parameter-time-equipment correlation data, and targeting the real-time operating status of industrial processes, the deviation between the target operating parameters and the actual operating parameters is calculated in real time. Combined with the real-time operating characteristics of the air conditioning equipment, real-time dynamic adjustment instructions are generated. The real-time dynamic adjustment instructions include the parameter adjustment direction, adjustment range, and execution time, and the frequency of instruction generation is synchronized with the frequency of process status changes. Based on the time period division in the industrial process sequence arrangement, and combined with the process demand intensity corresponding to each time period and the differences in the operating characteristics of air conditioning equipment in different time periods, the target operating parameters of each time period are adapted and adjusted in a time-specific manner to generate a time-segmented energy-saving control strategy. The time-segmented energy-saving control strategy clarifies the range of core air conditioning operating parameters, module start-stop rules and energy consumption control benchmarks for each time period.

7. A customized energy-saving air conditioning control device for industrial process needs, characterized in that, The device includes: The acquisition module is used to acquire real-time process parameters, environmental data and historical energy consumption records of air conditioning operation in industrial production. It uses Kalman filtering algorithm to remove electromagnetic interference and equipment vibration noise in the industrial environment and generate a standardized process-environment-energy consumption correlation data sequence. The processing module converts standardized process-environment-energy consumption correlation data sequences into three-dimensional process load distribution maps. After processing with fluid dynamics simulation software, an adaptive mesh generation algorithm is used to subdivide high-load process areas. Combined with the differences in thermal and humidity characteristics across different industrial scenarios, an individualized dynamic load prediction model for air conditioning is constructed. Based on this model, priority factors for different industrial processes are extracted to construct a dynamic parameter adjustment matrix. Parallel calculations are performed on the operating states of multiple air conditioning modules to obtain the combination of air conditioning operating parameters under the target energy consumption. Energy consumption peaks, load fluctuation rates, and process-energy consumption matching differences are extracted according to industrial process scenarios to classify energy consumption exceedance risk levels. A system is constructed that includes process demand intensity, environmental interference coefficient, and equipment energy efficiency degradation information. The system generates a multidimensional feature matrix of energy consumption data; compares real-time energy consumption with historical data from the same period and process, identifies abnormal signals such as short-term energy consumption spikes and load-energy consumption imbalances, and generates dynamic correction factors for energy consumption optimization using the slope of the energy consumption-process parameter correlation curve; groups users based on the industrial enterprise's production scale, process complexity, and equipment configuration, and uses a gradient boosting tree algorithm to screen key influencing factors of the multidimensional feature matrix and dynamic correction factors for energy consumption optimization; integrates energy consumption optimization parameters, process constraints, and equipment operating limit information to construct a personalized energy-saving control model; based on the target operating parameter output of the personalized energy-saving control model, and combined with the time correlation information of industrial process timing and air conditioning equipment operating characteristics, generates real-time dynamic adjustment instructions and time-segmented energy-saving control strategies.

8. An electronic device, characterized in that, include: First processor; and memory for storing executable instructions of the first processor; The first processor is configured to execute the customized energy-saving air conditioning control method for industrial process needs as described in any one of claims 1 to 6 by executing the executable instructions.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the second processor, it implements the customized energy-saving air conditioning control method for industrial process needs as described in any one of claims 1 to 6.

Images