Energy-saving intelligent raw material stirring control system for medical engineering

Abstract

The invention discloses a medical engineering energy-saving type raw material stirring intelligent control system, and relates to the technical field of medical engineering raw material stirring. The energy-saving intelligent raw material stirring control system for medical engineering comprises a data collection module, an energy consumption prediction module, an operation analysis module and an adjustment processing module. The real-time operation data are collected and preprocessed to obtain the first real-time operation data, then the first real-time operation data are input into the energy consumption prediction model to obtain the energy consumption prediction data and the reference data, then whether the energy consumption prediction data exceed the preset energy consumption range or not is judged, and if the energy consumption prediction data exceed the preset energy consumption range, the reference data is obtained. If yes, combining the first real-time operation data with the reference data to obtain an operation conformity coefficient, and finally obtaining an operation adjustment scheme according to the operation conformity coefficient and sending the operation adjustment scheme to preset personnel for processing, so that the effect of reducing energy consumption in the stirring process of the medical engineering raw materials is achieved. The problem that in the prior art, energy consumption is high in the traditional Chinese medicine engineering raw material stirring process is solved.

Description

Technical Field

[0001] The invention relates to the technical field of raw material stirring of pharmaceutical engineering, and in particular to an energy-saving raw material stirring intelligent control system for pharmaceutical engineering. Background Art

[0002] With the continuous development of modern medicine, pharmaceutical engineering is also evolving and progressing. Pharmaceutical engineering is a comprehensive, high-tech discipline that aims to apply the principles and methods of modern natural science and engineering technology to study the structure, function and interrelationships of the human body at multiple levels from an engineering perspective, reveal life phenomena, and provide new technical means for disease prevention, diagnosis, treatment and rehabilitation services. Pharmaceutical engineering covers a wide range of areas, including but not limited to biomedical engineering, chemical engineering and other disciplines. Pharmaceutical engineering is committed to integrating engineering disciplines and pharmaceutical knowledge to promote drug research and development, production process optimization and innovation of pharmaceutical equipment. In the pharmaceutical process, raw material stirring is a key step, which plays a key role in mixing, dissolving, promoting reactions and quality control. It directly affects the uniformity of the ingredients, efficacy and stability of the final drug, and is an indispensable and important link in the pharmaceutical process.

[0003] In the existing pharmaceutical process, pharmaceutical factories usually use refrigerants or cooling circulation systems to keep the temperature of stirring equipment and stirring containers within the required low temperature range. In addition, they also need to use electric heaters and other methods to add heat energy to the raw materials under low temperature conditions to maintain a specific reaction temperature or prevent overcooling, thereby maintaining the temperature stability of the stirring equipment and raw materials throughout the pharmaceutical process.

[0004] For example, the patent application with publication number: CN117270472A discloses a metallurgical powder making intelligent control system and process equipment thereof, including: a data acquisition unit, a server and a control unit. The data acquisition unit is used to collect the operating parameters of the powder making equipment, the server is connected to the data acquisition unit, the server is used to obtain and store the operating parameters collected by the data acquisition unit, and determine the control parameters according to the preset process data model, the control unit is connected to the server, the control unit is used to receive the control parameters output by the server, and control the operation of the powder making equipment according to the control parameters, so as to reduce the energy consumption of the powder making equipment and improve the utilization rate of the powder making equipment.

[0005] For example, the invention patent with announcement number: CN117170334B announces an intelligent control method and system for rapid fusion of medicines, including: setting the temperature limit space for medicine fusion, then performing fitting control of the medicine in the space, and performing control optimization on the fitting results, optimizing the performance effect of the reactor, generating an optimization space, and then reading the medicine data, and configuring the medicine dosage and addition order based on the medicine data and the optimization space, using it as the basic data for fusion, determining the temperature control space, performing synchronous optimization of the stirring parameters, and completing intelligent control. This application mainly solves the problem that traditional medicine fusion relies on manual operation and management, and there are problems such as irregular operation and insufficient precision, which may lead to unstable quality of medicines. By optimizing the performance of the reactor and then real-time monitoring and control of the medicine fusion process, waste and loss in the drug production process can be reduced, and the output and quality of drug production can be improved.

[0006] However, in the process of implementing the technical solution of the invention in the embodiments of the present application, the present application found that the above technology has at least the following technical problems: In the prior art, the frequency of failure of the stirring equipment may increase in a high temperature or humid environment, and the parameters of the stirring equipment, such as the stirring rate, may also affect the operation of the stirring equipment, resulting in a problem of high energy consumption during the stirring of pharmaceutical engineering raw materials. Summary of the invention

[0007] The embodiment of the present application solves the problem of high energy consumption in the process of stirring raw materials for pharmaceutical engineering in the prior art by providing an intelligent control system for energy-saving raw material stirring for pharmaceutical engineering, thereby achieving a reduction in energy consumption in the process of stirring raw materials for pharmaceutical engineering.

[0008] The embodiment of the present application provides an energy-saving raw material mixing intelligent control system for pharmaceutical engineering, comprising: a data collection module, an energy consumption prediction module, an operation analysis module and an adjustment processing module; wherein the data collection module is used to collect real-time operation data within a preset time interval and perform preprocessing to obtain first real-time operation data, thereby obtaining an operation accuracy coefficient, and the operation accuracy coefficient is used to comprehensively quantify the accuracy of the preprocessing; the energy consumption prediction module is used to input the first real-time operation data into the constructed energy consumption prediction model to obtain energy consumption prediction data, and determine whether the obtained energy consumption prediction data exceeds the preset energy consumption range, if it exceeds the preset energy consumption range, the corresponding first real-time operation data is transmitted to the operation analysis module, otherwise no processing is performed; the operation analysis module is used to compare the first real-time operation data with the reference data corresponding to the energy consumption prediction data to obtain an operation compliance coefficient, and the operation compliance coefficient is used to comprehensively quantify the degree of compliance between the real-time operation data within the preset time interval and the preset operation range; the adjustment processing module is used to obtain an operation adjustment plan according to the operation compliance coefficient, and send the operation adjustment plan to a preset person for processing.

[0009] Furthermore, the data collection module includes a data collection unit, a data processing unit and a data comparison unit; the data collection unit is used to collect real-time operation data within a preset time interval and transmit it to the data processing unit and the data comparison unit, and the real-time operation data includes stirring equipment data and environmental data; the data processing unit is used to pre-process the received real-time operation data to obtain first real-time operation data, and transmit the first real-time operation data to the data comparison unit; the data comparison unit is used to obtain an operation accuracy coefficient based on the received real-time operation data and the first real-time operation data.

[0010] Furthermore, the energy consumption prediction module includes an energy consumption prediction unit and a comparison and judgment unit; the energy consumption prediction unit is used to input the first real-time operation data into the constructed energy consumption prediction model to obtain energy consumption prediction data, and obtain corresponding reference data based on the energy consumption prediction data; the comparison and judgment unit is used to receive the energy consumption prediction data transmitted by the energy consumption prediction unit, and compare the energy consumption prediction data with the preset energy consumption range. If the energy consumption prediction data exceeds the preset energy consumption range, the first real-time operation data and reference data corresponding to the energy consumption prediction data exceeding the preset energy consumption range are transmitted to the operation analysis module.

[0011] Furthermore, the operation analysis module includes an equipment analysis unit and an environment analysis unit; the equipment analysis unit is used to receive first stirring equipment data and reference stirring equipment data, thereby obtaining an equipment compliance coefficient, and the equipment compliance coefficient is used to quantify the degree of compliance between the stirring equipment data and the reference stirring equipment data within a preset time interval; the environment analysis unit is used to receive first environment data and reference environment data, thereby obtaining an environment compliance coefficient, and the environment compliance coefficient is used to quantify the degree of compliance between the environment data and the reference environment data within a preset time interval.

[0012] Furthermore, the adjustment processing module includes an equipment adjustment unit and an environment adjustment unit; the equipment adjustment unit is used to obtain the equipment data to be adjusted according to the equipment compliance coefficient, thereby obtaining the corresponding equipment adjustment plan, and sending the equipment adjustment plan to the preset personnel for corresponding processing; the environment adjustment unit is used to obtain the environment data to be adjusted according to the environment compliance coefficient, thereby obtaining the corresponding environment adjustment plan, and sending the environment adjustment plan to the preset personnel for corresponding processing.

[0013] Furthermore, the specific method for obtaining the operation accuracy coefficient is as follows: obtaining the operation accuracy influence weight from the preset database, the operation accuracy influence weight includes the stirring device speed weight, the stirring device operating temperature weight, the stirring device service life weight, the ambient temperature weight and the ambient humidity weight; obtaining the operation accuracy reference error from the preset database; obtaining the operation accuracy coefficient according to the first real-time operation data, the real-time operation data, the operation accuracy influence weight and the operation accuracy reference error, and the operation accuracy coefficient is calculated using the following formula: ; In the formula, is the operation accuracy coefficient, is the speed weight of the mixing equipment, is the stirring equipment speed, is the speed of the first stirring device, is the reference error of the stirring equipment speed, The operating temperature weight for the mixing equipment, is the operating temperature of the mixing equipment, is the operating temperature of the first stirring device, The reference error of the operating temperature of the stirring equipment. is the service life weight of the mixing equipment, The service life of the mixing equipment. The service life of the first mixing equipment, It is the reference error of the service life of the mixing equipment. is the ambient temperature weight, is the ambient temperature, is the first ambient temperature, is the ambient temperature reference error, is the ambient humidity weight, is the ambient humidity, is the first ambient humidity, is the ambient humidity reference error.

[0014] Furthermore, the specific construction steps of the energy consumption prediction model are as follows: step one, construct a feature data set, and divide the feature data set into a training feature data set and a verification feature data set according to a preset ratio; step two, obtain a training model, and the training model is a converged model obtained by training a preset model using the training feature data set; step three, input the verification feature data set into the constructed training model for model verification, and optimize the training model according to the result of the model verification to obtain the energy consumption prediction model.

[0015] Furthermore, the specific method for obtaining the equipment compliance coefficient is as follows: obtain the equipment compliance influence weight and the equipment compliance reference deviation from the preset database, the equipment compliance influence weight includes the first stirring device speed weight, the first stirring device operating temperature weight, and the first stirring device service life weight; obtain the equipment compliance coefficient according to the first stirring device data, the reference stirring device data, the equipment compliance influence weight and the equipment compliance reference deviation, and the equipment compliance coefficient is calculated using the following formula: ; Where C is the equipment compliance coefficient, is the speed weight of the first stirring device, is the speed of the first stirring device, For reference stirring equipment speed, is the reference deviation of the stirring equipment speed, The operating temperature weight of the first stirring device, is the operating temperature of the mixing equipment, For reference, the operating temperature of the mixing equipment, It is the reference deviation of the operating temperature of the mixing equipment. is the service life weight of the first mixing equipment, The service life of the mixing equipment. For reference to the service life of mixing equipment, It is the reference deviation of the service life of mixing equipment.

[0016] Furthermore, the specific method for obtaining the environmental compliance coefficient is as follows: obtaining an environmental compliance impact weight and an environmental compliance reference deviation from a preset database, wherein the environmental compliance impact weight includes a first environmental temperature weight and a first environmental humidity weight; obtaining an environmental compliance coefficient according to the first environmental data, the reference environmental data, the environmental compliance impact weight and the environmental compliance reference deviation, wherein the environmental compliance coefficient is calculated using the following formula: ; Where E is the environmental compliance coefficient, is the first ambient temperature weight, is the first ambient temperature, is the reference ambient temperature, is the ambient temperature reference deviation, is the first environmental humidity weight, is the first ambient humidity, is the reference ambient humidity, is the ambient humidity reference deviation.

[0017] Furthermore, the specific process of obtaining the operation adjustment plan based on the operation compliance coefficient is as follows: determine whether the equipment compliance coefficient is less than the preset equipment compliance threshold. If it is less than the preset equipment compliance threshold, obtain the equipment data to be adjusted based on the reference mixing equipment data, and obtain the equipment adjustment plan based on this, and send the equipment adjustment plan to the preset personnel for processing; determine whether the environment compliance coefficient is less than the preset environment compliance threshold. If it is less than the preset environment compliance threshold, obtain the environment data to be adjusted based on the reference environment data, and obtain the environment adjustment plan based on this, and send the environment adjustment plan to the preset personnel for processing.

[0018] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: 1. The first real-time operation data is obtained by collecting real-time operation data and performing preprocessing, and then the first real-time operation data is input into the energy consumption prediction model to obtain energy consumption prediction data and obtain reference data, and then it is determined whether the energy consumption prediction data exceeds the preset energy consumption range. If it exceeds the preset energy consumption range, the first real-time operation data is combined with the reference data to obtain the operation compliance coefficient, and finally the operation adjustment plan is obtained according to the operation compliance coefficient and sent to the preset personnel for processing, thereby improving the production efficiency of raw material mixing, and then realizing the reduction of energy consumption in the process of mixing raw materials for pharmaceutical engineering, and effectively solving the problem of high energy consumption in the process of mixing raw materials for pharmaceutical engineering in the prior art.

[0019] 2. By obtaining the energy consumption prediction data output by the energy consumption prediction model, and then calculating the corresponding reference mixing equipment data based on the obtained energy consumption prediction data, and finally calculating the degree of conformity between the first mixing equipment data and the reference mixing equipment data to obtain the equipment conformity coefficient, the numerical evaluation of the degree of conformity between the first mixing equipment data and the reference mixing equipment data is realized, thereby achieving a more accurate evaluation of the equipment conformity.

[0020] 3. By obtaining the energy consumption prediction data output by the energy consumption prediction model, and then calculating the corresponding reference environmental data based on the obtained energy consumption prediction data, and finally calculating the degree of compliance between the first environmental data and the reference environmental data to obtain the environmental compliance coefficient, the numerical evaluation of the degree of compliance between the first environmental data and the reference environmental data is realized, thereby achieving a more accurate evaluation of environmental compliance. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 A schematic diagram of the structure of an energy-saving raw material mixing intelligent control system for pharmaceutical engineering provided in an embodiment of the present application; Figure 2 A schematic diagram of the structure of a data collection module in a pharmaceutical engineering energy-saving raw material mixing intelligent control system system provided in an embodiment of the present application; Figure 3 A flowchart for constructing an energy consumption prediction model in an energy-saving raw material mixing intelligent control system for pharmaceutical engineering provided in an embodiment of the present application; Figure 4 A schematic diagram of the change in the device compliance coefficient provided in an embodiment of the present application. DETAILED DESCRIPTION

[0022] The embodiment of the present application solves the problem of high energy consumption in the raw material mixing process of pharmaceutical engineering in the prior art by providing an energy-saving intelligent control system for raw material mixing of pharmaceutical engineering. The first real-time operation data is collected within a preset time interval and pre-processed to obtain the first real-time operation data, and the operation accuracy coefficient is obtained accordingly. The first real-time operation data is then input into the constructed energy consumption prediction model to obtain energy consumption prediction data, and it is determined whether the obtained energy consumption prediction data exceeds the preset energy consumption range. If it exceeds the preset energy consumption range, the corresponding first real-time operation data is transmitted to the operation analysis module, otherwise it is not processed. The first real-time operation data is compared with the reference data corresponding to the energy consumption prediction data to obtain the operation compliance coefficient, and the operation adjustment plan is obtained according to the operation compliance coefficient. The operation adjustment plan is sent to the preset personnel for processing, thereby reducing the energy consumption in the raw material mixing process of pharmaceutical engineering.

[0023] The technical solution in the embodiment of the present application is to solve the problem of high energy consumption in the mixing process of the raw materials in the pharmaceutical engineering, and the overall idea is as follows: Energy consumption prediction data is obtained by inputting the preprocessed first real-time operation data into the energy consumption prediction model and obtaining reference data, and then judging whether the energy consumption prediction data exceeds the preset energy consumption range. If it exceeds the preset energy consumption range, the first real-time operation data is combined with the reference data to obtain the operation compliance coefficient. Finally, the operation adjustment plan is obtained according to the operation compliance coefficient and sent to the preset personnel for processing, thereby achieving the effect of reducing energy consumption in the mixing process of pharmaceutical engineering raw materials.

[0024] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0025] like Figure 1 As shown, it is a structural schematic diagram of an energy-saving raw material mixing intelligent control system for pharmaceutical engineering provided by an embodiment of the present application. The energy-saving raw material mixing intelligent control system for pharmaceutical engineering provided by an embodiment of the present application includes: a data collection module, an energy consumption prediction module, an operation analysis module and an adjustment processing module; the data collection module is used to collect real-time operation data within a preset time interval and perform preprocessing to obtain first real-time operation data, thereby obtaining an operation accuracy coefficient, and the operation accuracy coefficient is used to comprehensively quantify the accuracy of the preprocessing; the energy consumption prediction module is used to input the first real-time operation data into the constructed energy consumption prediction model to obtain energy consumption prediction data, and determine whether the obtained energy consumption prediction data exceeds the preset energy consumption range. If it exceeds the preset energy consumption range, the corresponding first real-time operation data is transmitted to the operation analysis module, otherwise it is not processed; the operation analysis module is used to compare the first real-time operation data with the reference data corresponding to the energy consumption prediction data to obtain an operation compliance coefficient, and the operation compliance coefficient is used to comprehensively quantify the degree of compliance between the real-time operation data within the preset time interval and the preset operation range; the adjustment processing module is used to obtain an operation adjustment plan according to the operation compliance coefficient, and send the operation adjustment plan to the preset personnel for processing.

[0026] In this embodiment, real-time operation data is mixing equipment data and environmental data collected in real time through a speed sensor and a temperature sensor installed on the mixing equipment and a temperature sensor and a humidity sensor installed in the environment where the equipment is located; the energy consumption prediction model is used to predict the energy consumption situation according to the first real-time operation data to obtain energy consumption prediction data, and obtain corresponding reference data according to the energy consumption prediction data; the preset energy consumption range for minimizing energy consumption is determined based on reference historical data, combined with equipment performance and production process requirements; the operation compliance coefficient includes an equipment compliance coefficient and an environmental compliance coefficient; the operation adjustment plan includes an equipment adjustment plan and an environmental adjustment plan; and the energy consumption is reduced during the mixing of pharmaceutical engineering raw materials.

[0027] Further, such as Figure 2As shown, it is a structural schematic diagram of a data collection module in an energy-saving raw material mixing intelligent control system for pharmaceutical engineering provided in an embodiment of the present application, the data collection module includes a data collection unit, a data processing unit and a data comparison unit; the data collection unit: is used to collect real-time operation data within a preset time interval and transmit it to the data processing unit and the data comparison unit, the real-time operation data includes mixing equipment data and environmental data; the data processing unit: is used to pre-process the received real-time operation data to obtain first real-time operation data, and transmit the first real-time operation data to the data comparison unit; the data comparison unit: obtains the operation accuracy coefficient according to the received real-time operation data and the first real-time operation data.

[0028] In this embodiment, the stirring equipment data includes the stirring equipment speed, the stirring equipment operating temperature, and the service life of the stirring equipment; the environmental data includes the environmental temperature data and the environmental humidity data; the preprocessing includes missing value filling, outlier removal and data interpolation processing; wherein, in data collection, data may be missing due to various reasons such as sensor failure and data transmission problems. If these missing values ​​are not processed, it will lead to information loss and model performance degradation; outliers are usually caused by measurement errors, equipment failures or other unforeseen factors. These values ​​will seriously interfere with the accuracy of data analysis, and therefore need to be identified and removed through statistical methods or domain knowledge; the first real-time operation data represents the corresponding data obtained by preprocessing the real-time operation data; the first real-time operation data includes the first stirring equipment data and the first environmental data, the first stirring equipment data includes the first stirring equipment speed, the first stirring equipment operating temperature and the service life of the first stirring equipment, and the first environmental data includes the first environmental temperature and the first environmental humidity; effective processing of real-time operation data is achieved.

[0029] Furthermore, the energy consumption prediction module includes an energy consumption prediction unit and a comparison and judgment unit; the energy consumption prediction unit is used to input the first real-time operation data into the constructed energy consumption prediction model to obtain energy consumption prediction data, and obtain corresponding reference data based on the energy consumption prediction data; the comparison and judgment unit is used to receive the energy consumption prediction data transmitted by the energy consumption prediction unit, and compare the energy consumption prediction data with the preset energy consumption range. If the energy consumption prediction data exceeds the preset energy consumption range, the first real-time operation data and reference data corresponding to the energy consumption prediction data exceeding the preset energy consumption range are transmitted to the operation analysis module, otherwise no processing is performed.

[0030] In this embodiment, the energy consumption prediction model is based on machine learning and can capture the laws and patterns in the data through the analysis and learning of historical data, and predict future energy consumption trends based on this, and output energy consumption prediction data, which indicates the amount of energy consumed by the mixing equipment within a preset time interval predicted by the energy consumption prediction model; the energy consumption prediction unit obtains reference data corresponding to the energy consumption prediction data by querying the database, calling the expert system or executing a specific algorithm based on the energy consumption prediction data, wherein the reference data includes reference mixing equipment data and reference environmental data, the reference mixing equipment data includes reference mixing equipment speed, reference mixing equipment operating temperature and reference mixing equipment service life, and the reference environmental data includes reference environmental temperature and reference environmental humidity; the prediction and judgment of energy consumption within a preset time interval is realized.

[0031] Furthermore, the operation analysis module includes an equipment analysis unit and an environment analysis unit; the equipment analysis unit is used to receive first stirring equipment data and reference stirring equipment data, and obtain an equipment compliance coefficient based on this; the equipment compliance coefficient is used to quantify the degree of compliance between the stirring equipment data within a preset time interval and the reference stirring equipment data; the environment analysis unit is used to receive first environment data and reference environment data, and obtain an environment compliance coefficient based on this; the environment compliance coefficient is used to quantify the degree of compliance between the environment data within a preset time interval and the reference environment data.

[0032] In this embodiment, the first real-time operation data is compared with the reference data corresponding to the energy consumption prediction data to obtain the operation compliance coefficient, wherein the operation compliance coefficient includes the equipment compliance coefficient and the environment compliance coefficient; the equipment analysis unit obtains the equipment compliance coefficient by comparing and analyzing the first stirring equipment data with the reference stirring equipment data, and the coefficient is a quantitative indicator used to intuitively reflect the degree of compliance between the actual operation state and the ideal operation state of the stirring equipment within a preset time interval; the higher the equipment compliance coefficient, the better the energy consumption and efficiency performance of the equipment operation; otherwise, measures may need to be taken to adjust or optimize; the environment analysis unit uses advanced sensing technology, environmental monitoring system and data analysis tools to comprehensively compare and analyze the first environmental data with the reference environmental data to obtain the environment compliance coefficient; the coefficient is also a quantitative indicator used to measure the degree of compliance between the actual environmental conditions and the optimal environmental conditions within a preset time interval, and the change of the environment compliance coefficient can reflect the potential impact of environmental factors on the efficiency and energy consumption of the stirring process, and provide an important reference basis for system optimization; the operation analysis module realizes comprehensive monitoring and evaluation of the operation state and environmental conditions of the stirring equipment through the collaborative work of the equipment analysis unit and the environment analysis unit.

[0033] Furthermore, the adjustment processing module includes an equipment adjustment unit and an environment adjustment unit; the equipment adjustment unit is used to obtain the equipment data to be adjusted according to the equipment compliance coefficient, thereby obtaining the corresponding equipment adjustment plan, and sending the equipment adjustment plan to the preset personnel for corresponding processing; the environment adjustment unit is used to obtain the environment data to be adjusted according to the environment compliance coefficient, thereby obtaining the corresponding environment adjustment plan, and sending the environment adjustment plan to the preset personnel for corresponding processing.

[0034] In this embodiment, the equipment data to be adjusted represents the data of the mixing equipment so that the predicted energy consumption data does not exceed the preset energy consumption range. Based on the equipment data to be adjusted, the equipment adjustment unit will use advanced algorithms and expert knowledge base to formulate an equipment adjustment plan, which includes replacing high-efficiency equipment components and optimizing equipment operating parameters, aiming to improve the operating efficiency and energy utilization rate of the equipment; the environmental data to be adjusted represents the environmental data so that the predicted energy consumption data does not exceed the preset energy consumption range. Based on the environmental data to be adjusted, the environmental adjustment unit will combine environmental science, engineering and energy management knowledge to formulate an environmental adjustment plan, which includes adjusting the workshop ventilation system, optimizing the workshop layout to reduce the heat island effect, installing temperature and humidity control equipment and other measures, aiming to improve the production environment and reduce energy consumption; and realize the formulation of specific measures to reduce energy consumption.

[0035] Furthermore, the specific method for obtaining the operation accuracy coefficient is as follows: obtaining the operation accuracy influence weight from the preset database, the operation accuracy influence weight includes the mixing equipment speed weight, the mixing equipment operating temperature weight, the mixing equipment service life weight, the ambient temperature weight and the ambient humidity weight; obtaining the operation accuracy reference error from the preset database; obtaining the operation accuracy coefficient according to the first real-time operation data, the real-time operation data, the operation accuracy influence weight and the operation accuracy reference error, and the operation accuracy coefficient is calculated using the following formula: ; In the formula, is the operation accuracy coefficient, is the speed weight of the mixing equipment, is the stirring equipment speed, is the speed of the first stirring device, is the reference error of the stirring equipment speed, The operating temperature weight for the mixing equipment, is the operating temperature of the mixing equipment, is the operating temperature of the first stirring device, The reference error of the operating temperature of the stirring equipment. is the service life weight of the mixing equipment, The service life of the mixing equipment. The service life of the first mixing equipment, It is the reference error of the service life of the mixing equipment. is the ambient temperature weight, is the ambient temperature, is the first ambient temperature, is the ambient temperature reference error, is the ambient humidity weight, is the ambient humidity, is the first ambient humidity, is the ambient humidity reference error.

[0036] In this embodiment, the formula combines the first real-time operation data, the real-time operation data, the operation accuracy impact weight and the operation accuracy reference error to obtain the operation accuracy coefficient. In this formula, the absolute value of the difference between the first real-time operation data and the real-time operation data is positively correlated with the operation accuracy coefficient. The smaller the absolute value of the difference between the first real-time operation data and the real-time operation data, the smaller the operation accuracy coefficient. The larger the absolute value of the difference between the first real-time operation data and the real-time operation data, the larger the operation accuracy coefficient. This shows that the integrity and accuracy of the real-time operation data will significantly affect the first real-time operation data obtained by preprocessing. When the speed of the stirring device is higher, the operating temperature of the stirring device may also increase, which may lead to a reduction in the service life of the stirring device; when the ambient temperature increases, the ambient humidity may decrease; when the speed of the first stirring device is higher, the operating temperature of the first stirring device may also increase, which may lead to a reduction in the service life of the first stirring device; when the first ambient temperature increases, the first ambient humidity may decrease; the closer the operation accuracy coefficient is to 0, the higher the effectiveness and accuracy of the preprocessing step. When the operation accuracy coefficient is higher than a certain threshold, corrective measures may need to be taken to improve the operation accuracy; the stirring device speed weight represents the influence of the stirring device speed on the operation accuracy coefficient. The weight of the operating temperature of the mixing equipment indicates the influence of the operating temperature of the mixing equipment on the operation accuracy coefficient, the weight of the service life of the mixing equipment indicates the influence of the service life of the mixing equipment on the operation accuracy coefficient, the weight of the ambient temperature indicates the influence of the ambient temperature on the operation accuracy coefficient, and the weight of the ambient humidity indicates the influence of the ambient humidity on the operation accuracy coefficient; the operation accuracy reference error includes the reference error of the speed of the mixing equipment, the reference error of the operating temperature of the mixing equipment, the reference error of the service life of the mixing equipment, the reference error of the ambient temperature and the reference error of the ambient humidity. The sum of the weight of the speed of the mixing equipment, the weight of the operating temperature of the mixing equipment, the weight of the service life of the mixing equipment, the weight of the ambient temperature and the weight of the ambient humidity is 1, indicating the different influences of different factors on the operation accuracy coefficient. Adjusting the distribution of weights can reflect the different influences of different factors on the operation accuracy coefficient; in the formula, the reference error of each parameter (such as the reference error of the speed of the mixing equipment, the reference error of the operating temperature of the mixing equipment, etc.) is used to determine the acceptable deviation range between the real-time operation data and the first real-time operation data; it is helpful to distinguish normal measurement fluctuations from real anomalies or errors; by calculating the square value of the difference between the real-time operation data and the first real-time operation data divided by the square value of the reference error, and considering its weight, the formula can more accurately evaluate the operation accuracy; Specifically, the stirring device speed weight is obtained from a preset database. In a specific embodiment, a fitting curve is obtained by fitting the relationship between the stirring device speed and the operation accuracy coefficient in a historical time period, and the stirring device speed weight corresponding to the input stirring device speed is obtained according to the fitting curve.

[0037] The operating temperature weight of the stirring device is obtained from a preset database. In a specific embodiment, a fitting curve is obtained by fitting the relationship between the operating temperature of the stirring device and the operation accuracy coefficient in a historical time period, and the operating temperature weight of the stirring device corresponding to the input operating temperature of the stirring device is obtained according to the fitting curve.

[0038] The service life weight of the mixing equipment is obtained from a preset database. In a specific embodiment, a fitting curve is obtained by fitting the relationship between the service life of the mixing equipment and the operation accuracy coefficient in a historical time period, and the service life weight of the mixing equipment corresponding to the input service life of the mixing equipment is obtained according to the fitting curve.

[0039] The ambient temperature weight is obtained from a preset database. In a specific embodiment, a fitting curve is obtained by fitting the relationship between the ambient temperature and the operation accuracy coefficient in a historical time period, and the ambient temperature weight corresponding to the input ambient temperature is obtained according to the fitting curve.

[0040] The ambient humidity weight is obtained from a preset database. In a specific embodiment, a fitting curve is obtained by fitting the relationship between the ambient humidity and the operation accuracy coefficient in a historical time period, and the ambient humidity weight corresponding to the input ambient humidity is obtained according to the fitting curve.

[0041] The reference error of the speed of the stirring equipment is used to quantify the maximum allowable difference or standard deviation between the speed of the stirring equipment and the speed of the first stirring equipment, reflecting the uncertainty of speed measurement and the acceptable fluctuation range, and is expressed by summing and averaging the collected historical stirring speed data of the stirring equipment; the reference error of the operating temperature of the stirring equipment is used to quantify the maximum allowable difference or standard deviation between the operating temperature of the stirring equipment and the operating temperature of the first stirring equipment, measuring the uncertainty of temperature measurement and the fluctuation within the acceptable range, and is expressed by summing and averaging the collected historical stirring temperature data of the stirring equipment; the reference error of the service life of the stirring equipment is used to quantify the allowable difference or standard deviation between the service life of the stirring equipment and the service life of the first stirring equipment. Since the service life is usually not continuous, the reference error of the stirring equipment service life is used to quantify the maximum allowable difference or standard deviation between the service life of the stirring equipment and the service life of the first stirring equipment. The deviation here may more reflect the aging speed of the equipment or the uncertainty of the maintenance record, which is expressed by summing and averaging the collected historical data on the service life of the mixing equipment; the ambient temperature reference error is used to quantify the maximum allowable difference or standard deviation between the ambient temperature and the first ambient temperature, reflecting the uncertainty of temperature measurement and the acceptable fluctuation range, and is expressed by summing and averaging the collected historical ambient temperature data; the ambient humidity reference error is used to quantify the maximum allowable difference or standard deviation between the ambient humidity and the first ambient humidity, reflecting the uncertainty of humidity measurement and the acceptable fluctuation range, and is expressed by summing and averaging the collected historical ambient humidity data; the numerical evaluation of the effectiveness of the pre-processed real-time operation data is realized.

[0042] Further, such as Figure 3 As shown, it is a flow chart for constructing the energy consumption prediction model provided in an embodiment of the present application, and the specific steps for constructing the energy consumption prediction model are as follows: Step 1, construct a feature data set, and divide the feature data set into a training feature data set and a verification feature data set according to a preset ratio; Step 2, obtain a training model, and the training model is a converged model obtained by training a preset model using the training feature data set; Step 3, input the verification feature data set into the constructed training model for model verification, and optimize the training model according to the result of the model verification to obtain the energy consumption prediction model.

[0043] In this embodiment, the feature data set is a collection of the first real-time operation data in history, wherein the first real-time operation data in history represents the result of preprocessing the real-time operation data in the historical time period, and the preprocessing method is consistent with the preprocessing method for the real-time operation data, that is, missing value filling, outlier removal and data interpolation processing; the preset model is determined to be a long short-term memory network (Long Short-Term Memory, LSTM) model; the LSTM model is trained using the training feature data set, and the LSTM model parameters are adjusted by the optimization algorithm to minimize the prediction error until the model reaches a convergence state; the performance of the trained LSTM model is evaluated using the verification feature data set, and the structure or parameters of the LSTM model are adjusted according to the verification results to improve the performance; Specifically, the specific method of adjusting the model parameters through the optimization algorithm is as follows: first, a loss function is defined to measure the difference between the model prediction and the actual data, and then the gradient descent method is selected as the optimization algorithm. In each iteration, the gradient of the loss function with respect to the model parameters is calculated, and the parameter value is updated using this gradient to reduce the loss. This process is repeated until the model reaches a convergence state on the training data (the corresponding loss function no longer has a downward trend), thereby achieving the purpose of minimizing the prediction error of the energy consumption prediction model on the training data; and achieving accurate prediction of energy consumption within a preset time interval; It should be understood that the preset model refers to a machine learning or deep learning model that is initially selected based on a specific task (energy consumption prediction) and data characteristics (characteristics of the first real-time running data). The selection of this model usually depends on the nature of the data, the complexity of the prediction problem, and the prediction ability of the model; Long Short-Term Memory (LSTM) is a special recurrent neural network that is very suitable for processing and predicting important events with very long intervals and delays in time series data, because energy consumption data usually has time series characteristics (such as historical energy consumption data has an impact on future energy consumption); Taking LSTM as the preset model and the preset ratio of 7:3 as an example, first divide the feature data set into a training feature data set and a verification feature data set in a ratio of 7:3, that is, the training feature data set accounts for 70% of the feature data set, and the verification feature data set accounts for 30% of the feature data set. Then input the training feature data set into the LSTM model for training until convergence to obtain a training model, where convergence means that the corresponding loss curve no longer decreases (or tends to be flat). Then input the verification feature data set into the training model to obtain the mean square error, that is, the corresponding verification result refers to the mean square error obtained by inputting the verification feature data set into the trained training model, where the mean square error is used to measure the average of the squares of the difference between the model prediction value and the true value. It is a commonly used performance indicator in regression problems and is used to evaluate the generalization ability of the model on unseen data, that is, the prediction accuracy of the model for new data. The method of adjusting the LSTM model according to the verification results is mainly based on the mean square error on the verification set. First, adjust the structure of the LSTM model, which may include increasing or decreasing the implicit The number of hidden layers can be adjusted to balance the fitting ability and generalization ability of the model, or the number of neurons in each hidden layer can be adjusted to find the model complexity that best suits the current task. At the same time, the parameters of the model also need to be optimized. The learning rate is one of the key parameters, which determines the step size of the parameter update during the training process. If the learning rate is too large, the model may not be able to converge stably. If the learning rate is too small, the training process may be too slow. Adjusting the learning rate according to the verification results can accelerate the training process of the model and improve its prediction performance. In addition, regularization parameters (such as the dropout ratio) are also one of the key points of adjustment. Dropout is an effective method to prevent overfitting. It reduces the complexity of the model by randomly discarding a part of the neurons. Adjusting the dropout ratio according to the verification results can reduce the risk of overfitting while maintaining the model's prediction ability. Finally, the above process is repeated iteratively, that is, training the model, evaluating the verification results, and adjusting the model structure and parameters until the LSTM model with the best performance on the verification set is found.

[0044] Furthermore, the specific method for obtaining the equipment compliance coefficient is as follows: obtain the equipment compliance influence weight and the equipment compliance reference deviation from the preset database; the equipment compliance influence weight includes the first mixing equipment speed weight, the first mixing equipment operating temperature weight, and the first mixing equipment service life weight; obtain the equipment compliance coefficient according to the first mixing equipment data, the reference mixing equipment data, the equipment compliance influence weight and the equipment compliance reference deviation, and the equipment compliance coefficient is calculated using the following formula: ; Where C is the equipment compliance coefficient, is the speed weight of the first stirring device, is the speed of the first stirring device, For reference stirring equipment speed, is the reference deviation of the stirring equipment speed, The operating temperature weight of the first stirring device, is the operating temperature of the mixing equipment, For reference, the operating temperature of the mixing equipment, It is the reference deviation of the operating temperature of the mixing equipment. is the service life weight of the first mixing equipment, The service life of the mixing equipment. For reference to the service life of mixing equipment, It is the reference deviation of the service life of mixing equipment.

[0045] In this embodiment, the formula combines the first stirring device data, the reference stirring device data, the device compliance influence weight and the device compliance reference deviation to obtain the device compliance coefficient. In this formula, the absolute value of the difference between the first stirring device data and the reference stirring device data is negatively correlated with the device compliance coefficient. The smaller the absolute value of the difference between the first stirring device data and the reference stirring device data, the larger the device compliance coefficient. The larger the absolute value of the difference between the first stirring device data and the reference stirring device data, the smaller the device compliance coefficient. This shows that the accuracy of the first stirring device data will significantly affect the energy consumption prediction data predicted by the energy consumption prediction model, thereby affecting the corresponding reference stirring device data. When the speed of the first stirring device is higher, the operating temperature of the first stirring device may also increase, which may lead to a reduction in the service life of the first stirring device; when the speed of the reference stirring device is higher, the operating temperature of the reference stirring device may also increase, which may lead to a reduction in the service life of the reference stirring device. The service life of the equipment is reduced; the sum of the weight of the first stirring equipment speed, the weight of the first stirring equipment operating temperature and the weight of the first stirring equipment service life is 1, which indicates the different influences of different factors on the equipment compliance coefficient. Adjusting the distribution of weights can reflect the different influences of different factors on the equipment compliance coefficient; the equipment compliance reference deviation includes the stirring equipment speed reference deviation, the stirring equipment operating temperature reference deviation and the stirring equipment service life reference deviation; the weight of the first stirring equipment speed indicates the influence of the stirring equipment speed on the equipment compliance coefficient; the weight of the first stirring equipment operating temperature indicates the influence of the stirring equipment operating temperature on the equipment compliance coefficient; the weight of the first stirring equipment service life indicates the influence of the stirring equipment service life on the equipment compliance coefficient; in the formula, the reference deviation of each parameter is used to determine the acceptable deviation range between the first stirring equipment data and the reference stirring equipment data, which helps to distinguish normal measurement fluctuations from real anomalies or errors; Specifically, the first stirring device speed weight is obtained from a preset database. In a specific embodiment, a fitting curve is obtained by fitting the relationship between the first stirring device speed and the device compliance coefficient in a historical time period, and the first stirring device speed weight corresponding to the input first stirring device speed is obtained according to the fitting curve.

[0046] The operating temperature weight of the first stirring device is obtained from a preset database. In a specific embodiment, a fitting curve is obtained by fitting the relationship between the operating temperature of the first stirring device and the equipment compliance coefficient in a historical time period, and the operating temperature weight of the first stirring device corresponding to the input first stirring device and the operating temperature is obtained according to the fitting curve.

[0047] The weight of the service life of the first mixing equipment is obtained from a preset database. In a specific embodiment, a fitting curve is obtained by fitting the relationship between the service life of the first mixing equipment and the equipment compliance coefficient within a historical time period, and the weight of the service life of the first mixing equipment corresponding to the input service life of the first mixing equipment is obtained according to the fitting curve.

[0048] The reference deviation of the speed of the mixing equipment is used to quantify the maximum allowable difference or standard deviation between the speed of the first mixing equipment and the speed of the reference mixing equipment, reflecting the uncertainty of speed measurement and the acceptable fluctuation range, and is expressed by summing the collected historical mixing speed data of the mixing equipment and calculating the standard deviation; the reference deviation of the operating temperature of the mixing equipment is used to quantify the maximum allowable difference or standard deviation between the operating temperature of the first mixing equipment and the operating temperature of the reference mixing equipment, measuring the uncertainty of temperature measurement and the fluctuation within the acceptable range, and is expressed by summing the collected history of the mixing equipment and calculating the standard deviation; the reference deviation of the service life of the mixing equipment is used to quantify the allowable difference or standard deviation between the service life of the first mixing equipment and the service life of the reference mixing equipment. Since the service life is usually not a continuous change, the deviation here may more reflect the uncertainty of the equipment aging speed or maintenance records, and is expressed by summing the collected historical mixing equipment service life data and calculating the standard deviation; the numerical evaluation of the conformity between the first mixing equipment data and the reference mixing equipment data is realized.

[0049] It is important to understand that Figure 4 As shown, it is a schematic diagram of the change of the device compliance coefficient provided in the embodiment of the present application, where, =0.4, =0.4, =0.2, = 0.4, definition is the temperature compliance coefficient, is the speed compliance coefficient, that is ; It can be seen from the figure that the equipment compliance coefficient is negatively correlated with the speed compliance coefficient and the temperature compliance coefficient; when the speed compliance coefficient is smaller, the equipment compliance coefficient is larger; when the temperature compliance coefficient is smaller, the equipment compliance coefficient is larger; a more intuitive description of the change of the equipment compliance coefficient is achieved.

[0050] Furthermore, the specific method for obtaining the environmental compliance coefficient is as follows: obtaining the environmental compliance impact weight and the environmental compliance reference deviation from a preset database, the environmental compliance impact weight including the first environmental temperature weight and the first environmental humidity weight; obtaining the environmental compliance coefficient according to the first environmental data, the reference environmental data, the environmental compliance impact weight and the environmental compliance reference deviation, and the environmental compliance coefficient is calculated using the following formula: ; Where E is the environmental compliance coefficient, is the first ambient temperature weight, is the first ambient temperature, is the reference ambient temperature, is the ambient temperature reference deviation, is the first environmental humidity weight, is the first ambient humidity, is the reference ambient humidity, is the ambient humidity reference deviation; In this embodiment, the formula combines the first environmental data, the reference environmental data, the environmental compliance impact weight and the environmental compliance reference deviation to obtain the environmental compliance coefficient. In this formula, the absolute value of the difference between the first environmental data and the reference environmental data is negatively correlated with the environmental compliance coefficient. The smaller the absolute value of the difference between the first environmental data and the reference environmental data, the larger the environmental compliance coefficient. The larger the absolute value of the difference between the first environmental data and the reference environmental data, the smaller the environmental compliance coefficient. This shows that the accuracy of the first environmental data will significantly affect the energy consumption prediction data predicted by the energy consumption prediction model, thereby affecting the corresponding reference environmental data. When the temperature of the first environment increases, the humidity of the first environment may decrease. When the temperature of the reference environment increases, the humidity of the first environment may decrease. When the temperature rises, the reference environmental humidity may decrease; the sum of the first environmental temperature weight and the first environmental humidity weight is 1, indicating the different effects of different factors on the environmental compliance coefficient, and adjusting the distribution of weights can reflect the different effects of different factors on the environmental compliance coefficient; the environmental compliance reference deviation includes the environmental temperature reference deviation and the environmental humidity reference deviation, the first environmental temperature weight indicates the degree of influence of the environmental temperature on the environmental compliance coefficient, and the first environmental humidity weight indicates the degree of influence of the environmental humidity on the environmental compliance coefficient; in the formula, the reference deviation of each parameter is used to determine the acceptable deviation range between the first environmental data and the reference environmental data, which helps to distinguish normal measurement fluctuations from real anomalies or errors; Specifically, the first ambient temperature weight is obtained from a preset database. In a specific embodiment, a fitting curve is obtained by fitting the relationship between the first ambient temperature and the environmental compliance coefficient in a historical time period, and the first ambient temperature weight corresponding to the input first ambient temperature is obtained according to the fitting curve.

[0051] The first ambient humidity weight is obtained from a preset database. In a specific embodiment, a fitting curve is obtained by fitting the relationship between the first ambient humidity and the environmental compliance coefficient in a historical time period, and the first ambient humidity weight corresponding to the input first ambient humidity is obtained according to the fitting curve.

[0052] The ambient temperature reference deviation is used to quantify the maximum allowable difference or standard deviation between the first ambient temperature and the reference ambient temperature, reflecting the uncertainty of temperature measurement and the acceptable fluctuation range, and is expressed by summing the collected historical ambient temperature data and calculating the standard deviation; the ambient humidity reference deviation is used to quantify the maximum allowable difference or standard deviation between the first ambient humidity and the reference ambient humidity, reflecting the uncertainty of humidity measurement and the acceptable fluctuation range, and is expressed by summing the collected historical ambient humidity data and calculating the standard deviation; It should be understood that, taking the first ambient temperature weight as 0.5, the first ambient humidity weight as 0.5, the ambient temperature reference deviation as 0.3 and the ambient humidity reference deviation as 0.1 as an example, the change statistics of the environmental compliance coefficient are shown in Table 1: Table 1 Statistics of changes in environmental compliance coefficients First ambient temperature (Celsius) Reference ambient temperature (Celsius) First environment humidity (%) Reference ambient humidity (%) Environmental compliance coefficient E 25.0 25.0 50.0 50.0 1 25.2 25.0 50.0 50.0 0.68 25.0 25.0 50.5 50.0 0.74 25.3 24.8 49.8 50.0 0.40 ... ... ... ... ... As can be seen from Table 1, these four sets of data show the changes in environmental compliance coefficients under different temperature and humidity differences. In the first set, since there is no difference in temperature and humidity, the compliance coefficient is 1, indicating full compliance. In the other three sets, as the temperature and humidity differences increase, the environmental compliance coefficients decrease; the numerical evaluation of the compliance between the first environmental data and the reference environmental data is realized.

[0053] Furthermore, the specific process of obtaining the operation adjustment plan based on the operation compliance coefficient is as follows: determine whether the equipment compliance coefficient is less than the preset equipment compliance threshold. If it is less than the preset equipment compliance threshold, obtain the equipment data to be adjusted based on the reference mixing equipment data, and obtain the equipment adjustment plan accordingly, and send the equipment adjustment plan to the preset personnel for processing, otherwise no processing is performed; determine whether the environment compliance coefficient is less than the preset environment compliance threshold. If it is less than the preset environment compliance threshold, obtain the environment data to be adjusted based on the reference environment data, and obtain the environment adjustment plan accordingly, and send the environment adjustment plan to the preset personnel for processing, otherwise no processing is performed.

[0054] In this embodiment, if the equipment compliance coefficient is less than the preset equipment compliance threshold, it means that the current equipment operation state needs to be adjusted, and the system will identify which equipment parameters need to be adjusted based on the reference mixing equipment data, that is, obtain the equipment data to be adjusted. Based on the equipment data to be adjusted, the system will combine equipment performance, maintenance records, cost-effectiveness and other factors to formulate a detailed equipment adjustment plan, and then send the detailed equipment adjustment plan to the relevant preset personnel through the preset communication channel; if the environment compliance coefficient is less than the preset environment compliance threshold, it means that the current environmental conditions are not conducive to the efficient operation of the system and need to be adjusted; the system will identify which environmental factors need to be adjusted based on the reference environmental data, that is, obtain the environmental data to be adjusted; based on the environmental data to be adjusted, the system will formulate an environmental adjustment plan, which may include measures such as adjusting the workshop temperature, humidity, ventilation conditions, light intensity, etc., and then send the environmental adjustment plan to the preset personnel in a timely manner; Specifically, the method for obtaining the preset equipment compliance threshold is usually based on the analysis of historical operating data, reference to industry standards, and evaluation of actual production needs. Specifically, the company will collect and analyze the operating data of the mixing equipment over the past period of time, including key parameters such as equipment speed, operating temperature, and service life, as well as the relationship between these parameters and equipment operating efficiency and product quality. At the same time, it will also refer to relevant technical standards, specifications or best practices in the industry to determine the performance level that the equipment should achieve under ideal conditions; the method for obtaining the preset environmental compliance threshold usually involves a comprehensive consideration of industry standards, historical environmental data, production needs and safety specifications. The company will first collect and analyze the recommended values ​​or standard ranges for environmental parameters in the relevant industry, and then combine the changing trends and fluctuation ranges of its own historical environmental data to evaluate the impact of these parameters on product quality, production efficiency and personnel safety. On this basis, the company will also consider the specific needs, technical conditions and future development plans of the current production, and finally determine an environmental compliance threshold that meets both industry standards and its own production needs; achieving continuous optimization of mixing equipment parameters and environmental parameters.

[0055] To summarize, the embodiment of the present application collects real-time operation data and performs preprocessing to obtain first real-time operation data, then inputs the first real-time operation data into an energy consumption prediction model to obtain energy consumption prediction data and obtain reference data, and then determines whether the energy consumption prediction data exceeds a preset energy consumption range. If it exceeds the preset energy consumption range, the first real-time operation data is combined with the reference data to obtain an operation compliance coefficient, and finally an operation adjustment plan is obtained according to the operation compliance coefficient and sent to a preset person for processing, thereby improving the production efficiency of raw material mixing, thereby achieving a reduction in energy consumption in the process of mixing raw materials for pharmaceutical engineering, and effectively solving the problem of high energy consumption in the process of mixing raw materials for pharmaceutical engineering in the prior art.

[0056] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0057] The present invention is described with reference to flowcharts and / or block diagrams of systems, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0058] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0059] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0060] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0061] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. An energy-saving intelligent control system for raw material mixing in pharmaceutical engineering, characterized in that: include: Data collection module, energy consumption prediction module, operation analysis module and adjustment processing module; The data collection module is used to collect real-time operation data within a preset time interval and perform preprocessing to obtain first real-time operation data, thereby obtaining an operation accuracy coefficient, and the operation accuracy coefficient is used to comprehensively quantify the accuracy of the preprocessing; The energy consumption prediction module is used to input the first real-time operation data into the constructed energy consumption prediction model to obtain energy consumption prediction data, and determine whether the obtained energy consumption prediction data exceeds the preset energy consumption range. If it exceeds the preset energy consumption range, the corresponding first real-time operation data is transmitted to the operation analysis module, otherwise no processing is performed; The operation analysis module is used to compare the first real-time operation data with the reference data corresponding to the energy consumption prediction data to obtain an operation compliance coefficient, and the operation compliance coefficient is used to comprehensively quantify the degree of compliance between the real-time operation data within a preset time interval and the preset operation range; The adjustment processing module is used to obtain an operation adjustment plan according to the operation compliance coefficient, and send the operation adjustment plan to a preset person for processing.

2. The energy-saving intelligent control system for raw material mixing in pharmaceutical engineering as claimed in claim 1, characterized in that: The data collection module includes a data collection unit, a data processing unit and a data comparison unit; The data collection unit is used to collect real-time operation data within a preset time interval and transmit it to the data processing unit and the data comparison unit, wherein the real-time operation data includes stirring equipment data and environmental data; The data processing unit is used to pre-process the received real-time operation data to obtain first real-time operation data, and transmit the first real-time operation data to the data comparison unit; The data comparison unit is used to obtain an operation accuracy coefficient according to the received real-time operation data and the first real-time operation data.

3. The energy-saving intelligent control system for raw material mixing in pharmaceutical engineering as claimed in claim 1, characterized in that: The energy consumption prediction module includes an energy consumption prediction unit and a comparison and judgment unit; The energy consumption prediction unit is used to input the first real-time operation data into the constructed energy consumption prediction model to obtain energy consumption prediction data, and obtain corresponding reference data according to the energy consumption prediction data; The comparison and judgment unit is used to receive the energy consumption prediction data transmitted by the energy consumption prediction unit, and compare the energy consumption prediction data with the preset energy consumption range. If the energy consumption prediction data exceeds the preset energy consumption range, the first real-time operation data and reference data corresponding to the energy consumption prediction data exceeding the preset energy consumption range are transmitted to the operation analysis module.

4. The energy-saving intelligent control system for raw material mixing in pharmaceutical engineering as claimed in claim 1, characterized in that: The operation analysis module includes an equipment analysis unit and an environment analysis unit; The equipment analysis unit is used to receive the first stirring equipment data and the reference stirring equipment data, and obtain the equipment compliance coefficient based on the first stirring equipment data and the reference stirring equipment data, wherein the equipment compliance coefficient is used to quantify the degree of compliance between the stirring equipment data and the reference stirring equipment data within a preset time interval; The environmental analysis unit is used to receive the first environmental data and the reference environmental data, and obtain an environmental compliance coefficient based on the first environmental data and the reference environmental data, wherein the environmental compliance coefficient is used to quantify the degree of compliance between the environmental data and the reference environmental data within a preset time interval.

5. The energy-saving intelligent control system for raw material mixing in pharmaceutical engineering as claimed in claim 1, characterized in that: The adjustment processing module includes a device adjustment unit and an environment adjustment unit; The equipment adjustment unit is used to obtain the equipment data to be adjusted according to the equipment compliance coefficient, obtain the corresponding equipment adjustment plan based on the equipment compliance coefficient, and send the equipment adjustment plan to the preset personnel for corresponding processing; The environment adjustment unit is used to obtain the environment data to be adjusted according to the environment compliance coefficient, obtain the corresponding environment adjustment plan based on the environment data, and send the environment adjustment plan to the preset personnel for corresponding processing.

6. The energy-saving intelligent control system for raw material mixing in pharmaceutical engineering as claimed in claim 2, characterized in that: The specific method for obtaining the operation accuracy coefficient is as follows: Obtaining accurate operation impact weights from a preset database, wherein the accurate operation impact weights include a stirring device speed weight, a stirring device operating temperature weight, a stirring device service life weight, an ambient temperature weight, and an ambient humidity weight; Obtain accurate reference error of operation from preset database; The operation accuracy coefficient is obtained according to the first real-time operation data, the real-time operation data, the operation accuracy influence weight and the operation accuracy reference error. The operation accuracy coefficient is calculated using the following formula: ； In the formula, is the operation accuracy coefficient, is the speed weight of the mixing equipment, is the stirring equipment speed, is the speed of the first stirring device, is the reference error of the stirring equipment speed, The operating temperature weight for the mixing equipment, is the operating temperature of the mixing equipment, is the operating temperature of the first stirring device, The reference error of the operating temperature of the stirring equipment. is the service life weight of the mixing equipment, The service life of the mixing equipment. The service life of the first mixing equipment, It is the reference error of the service life of the mixing equipment. is the ambient temperature weight, is the ambient temperature, is the first ambient temperature, is the ambient temperature reference error, is the ambient humidity weight, is the ambient humidity, is the first ambient humidity, is the ambient humidity reference error.

7. The energy-saving intelligent control system for raw material mixing in pharmaceutical engineering as claimed in claim 3, characterized in that: The specific steps of constructing the energy consumption prediction model are as follows: Step 1: construct a feature data set and divide the feature data set into a training feature data set and a verification feature data set according to a preset ratio; Step 2: Obtain a training model, where the training model is a converged model obtained by training a preset model using a training feature data set; Step three, input the verification feature data set into the constructed training model for model verification, and optimize the training model according to the results of the model verification to obtain the energy consumption prediction model.

8. The energy-saving intelligent control system for raw material mixing in pharmaceutical engineering as claimed in claim 4, characterized in that: The specific method for obtaining the device compliance coefficient is as follows: Obtaining equipment compliance impact weights and equipment compliance reference deviations from a preset database, wherein the equipment compliance impact weights include a first stirring equipment speed weight, a first stirring equipment operating temperature weight, and a first stirring equipment service life weight; The equipment compliance coefficient is obtained according to the first stirring equipment data, the reference stirring equipment data, the equipment compliance influence weight and the equipment compliance reference deviation. The equipment compliance coefficient is calculated using the following formula: ； Where C is the equipment compliance coefficient, is the speed weight of the first stirring device, is the speed of the first stirring device, For reference stirring equipment speed, is the reference deviation of the stirring equipment speed, The operating temperature weight of the first stirring device, is the operating temperature of the mixing equipment, For reference, the operating temperature of the mixing equipment, It is the reference deviation of the operating temperature of the mixing equipment. is the service life weight of the first mixing equipment, The service life of the mixing equipment. For reference to the service life of mixing equipment, It is the reference deviation of the service life of mixing equipment.

9. The energy-saving intelligent control system for raw material mixing in pharmaceutical engineering as claimed in claim 4, characterized in that: The specific method for obtaining the environmental compliance coefficient is as follows: Acquire an environmental compliance impact weight and an environmental compliance reference deviation from a preset database, wherein the environmental compliance impact weight includes a first environmental temperature weight and a first environmental humidity weight; The environmental compliance coefficient is obtained according to the first environmental data, the reference environmental data, the environmental compliance impact weight and the environmental compliance reference deviation, and the environmental compliance coefficient is calculated using the following formula: ； Where E is the environmental compliance coefficient, is the first ambient temperature weight, is the first ambient temperature, is the reference ambient temperature, is the ambient temperature reference deviation, is the first environmental humidity weight, is the first ambient humidity, is the reference ambient humidity, is the ambient humidity reference deviation.

10. The energy-saving intelligent control system for raw material mixing in pharmaceutical engineering as claimed in claim 1, characterized in that: The specific process of obtaining the operation adjustment plan according to the operation compliance coefficient is as follows: Determine whether the equipment compliance coefficient is less than the preset equipment compliance threshold. If it is less than the preset equipment compliance threshold, obtain the equipment data to be adjusted according to the reference mixing equipment data, obtain the equipment adjustment plan based on it, and send the equipment adjustment plan to the preset personnel for processing; Determine whether the environmental compliance coefficient is less than the preset environmental compliance threshold. If it is less than the preset environmental compliance threshold, obtain the environmental data to be adjusted based on the reference environmental data, obtain the environmental adjustment plan based on this, and send the environmental adjustment plan to the preset personnel for processing.

Images