CN118734614A - An energy-saving optimization control method and system for screw air compressor station based on AI technology - Google Patents

Abstract

The present invention belongs to the field of air-conditioning and refrigeration control technology, and relates to an energy-saving optimization control method and system for a screw air compressor station based on AI technology. By comprehensively considering the layout, environment, equipment configuration and historical operation data of the target screw air compressor station, a comprehensive simulation of the overall operation status of the target screw air compressor station is achieved. In the test simulation process, the multi-machine scenario under the same condition and the single-machine scenario under all conditions are combined to accurately and efficiently screen the screw air compressors with abnormal energy consumption in the target screw air compressor station. The causes of the abnormal energy consumption of each abnormal air compressor are further traced from three dimensions: control unit abnormality, cooling unit abnormality and heat recovery unit abnormality, and targeted personalized optimization strategies are formulated accordingly. After the improvement of each abnormal air compressor is completed, the energy-saving optimization effect of each abnormal air compressor is evaluated and feedback is provided. This not only helps to solve the problem of abnormal energy consumption of screw air compressors, but also promotes a substantial improvement in the overall energy efficiency and management level of the screw air compressor station.

Description

An energy-saving optimization control method and system for screw air compressor station based on AI technology

Technical Field

The present invention belongs to the technical field of air conditioning and refrigeration control, and relates to an energy-saving optimization control method and system for a screw air compressor station based on AI technology.

Background Art

In air conditioning and refrigeration, screw air compressor stations play an important role. Screw air compressors are usually used in large-scale air conditioning and refrigeration systems. They can provide sufficient cooling capacity to cover a large area of space, handle a large amount of cooling load, and ensure the stability and comfort of indoor temperature. As an indispensable energy supply center for production lines, screw air compressor stations not only bear the heavy responsibility of supplying constant compressed air quality, but also their energy consumption level accounts for a significant share of the total energy consumption of industrial sites, which is directly related to the operating cost-effectiveness and ecological sustainable development goals of enterprises. Therefore, implementing efficient energy-saving optimization control strategies for screw air compressor stations is an urgent need to alleviate energy shortages and reduce production costs.

In the existing technology, the operation of screw air compressors is mostly focused on the immediate autonomous energy-saving optimization at the loading and unloading control level. On the one hand, there is a lack of in-depth analysis and review capabilities of historical operating data, which results in the system being unable to learn from historical data and identify potential energy consumption abnormality risks, thereby missing the opportunity to optimize future operating strategies through historical data.

On the other hand, the single-dimensional loading and unloading control strategy during the operation of the screw air compressor lacks a systematic and comprehensive optimization approach, and ignores the important impact of other key units of the screw air compressor on energy consumption, such as the cooling unit and the heat recovery unit. This limits the depth and breadth of the energy-saving optimization strategy and makes it difficult to achieve the optimal operation of the entire system.

Summary of the invention

In view of this, in order to solve the problems raised in the above background technology, an energy-saving optimization control method and system for a screw air compressor station based on AI technology is proposed.

The purpose of the present invention can be achieved through the following technical solutions: The first aspect of the present invention provides an energy-saving optimization control method for a screw air compressor station based on AI technology, including: S1. Collecting basic information of the target screw air compressor station, including station layout diagram, historical environmental parameters, technical configuration parameters and historical operating parameters of each screw air compressor of the same type and model, building a simulation model of the target screw station and creating an operating condition simulation test scenario.

S2. Perform simulation tests on each screw air compressor in the target screw air compressor station according to the working condition simulation test scenario, and screen out each screw air compressor with abnormal energy consumption in the target screw air compressor station, which are recorded as abnormal air compressors.

S3. Trace the causes of abnormal energy consumption of each abnormal air compressor.

S4. Develop optimization strategies for the causes of abnormal energy consumption of each abnormal air compressor, so as to improve each abnormal air compressor.

S5. Re-run simulation tests on each abnormal air compressor after improvement, evaluate the energy-saving optimization effect of each abnormal air compressor and provide feedback.

The second aspect of the present invention provides an energy-saving optimization control system for a screw air compressor station based on AI technology, comprising: a simulation model building module, an energy consumption anomaly screening module, an energy consumption anomaly tracing module, an optimization strategy formulation module, an energy-saving effectiveness evaluation module and a cloud database.

The simulation model building module is connected to the energy consumption anomaly screening module, the energy consumption anomaly screening module is connected to the energy consumption anomaly tracing module, the energy consumption anomaly tracing module is connected to the optimization strategy formulation module, the optimization strategy formulation module is connected to the energy-saving effectiveness evaluation module, and the cloud database is respectively connected to the energy consumption anomaly screening module and the energy consumption anomaly tracing module.

The simulation model building module is used to collect the basic information of the target screw air compressor station, including the station layout, historical environmental parameters, technical configuration parameters and historical operating parameters of each screw air compressor of the same type and model, build a simulation model of the target screw station and create operating simulation test scenarios.

The energy consumption anomaly screening module is used to perform simulation tests on the target screw air compressor station according to the operating condition simulation test scenario, and screen the screw air compressors with abnormal energy consumption in the target screw air compressor station, which are recorded as abnormal air compressors.

The energy consumption abnormality tracing module is used to trace the causes of abnormal energy consumption of each abnormal air compressor.

The optimization strategy formulation module is used to formulate optimization strategies for the abnormal causes of energy consumption of each abnormal air compressor, so as to improve each abnormal air compressor.

The energy-saving effectiveness evaluation module is used to re-simulate and test each abnormal air compressor after improvement, evaluate the energy-saving optimization effect of each abnormal air compressor and provide feedback.

The cloud database is used to store the reasonable operating power ratio range, loading performance curve and unloading performance curve of various types and models of screw air compressors specified by screw air compressor manufacturers.

Compared with the prior art, the beneficial effects of the present invention are as follows: (1) The present invention integrates the layout, environment, equipment configuration and historical operation data of the target screw air compressor station to achieve a comprehensive simulation of the overall operating status of the target screw air compressor station, which helps to more accurately map the energy efficiency performance of the screw air compressor under different working conditions and provide a basis for the formulation of optimized operation strategies.

(2) The present invention combines the multi-machine scenario with the full-condition single-machine scenario to create an operating condition simulation test scenario for the target screw air compressor station simulation model, which helps to more comprehensively and efficiently identify the abnormal energy consumption performance of the screw air compressor, and provides a scientific basis for the screening of screw air compressors with abnormal energy consumption in the target screw air compressor station.

(3) The present invention traces the causes of abnormal energy consumption of each abnormal air compressor from three dimensions: control unit abnormality, cooling unit abnormality and heat recovery unit abnormality, and formulates targeted and personalized optimization strategies based on the traced causes of abnormal energy consumption. This avoids the limitations and defects of energy-saving optimization measures in the single loading and unloading control dimension during the operation of screw air compressors in the prior art, and not only helps solve the problem of abnormal energy consumption of screw air compressors, but also promotes a significant improvement in the overall energy efficiency and management level of screw air compressor stations.

(4) The present invention re-simulates and tests each abnormal air compressor after improvement, evaluates the energy-saving optimization effect of each abnormal air compressor and provides feedback, prompting professional staff to further adjust the optimization strategy according to the evaluation results, forming a closed loop of continuous improvement, and continuously improving the energy efficiency level of the air compressor.

BRIEF DESCRIPTION OF THE DRAWINGS

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for describing the embodiments are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For passengers with ordinary technical skills in this field, other drawings can be obtained based on these drawings without creative work.

FIG. 1 is a schematic diagram of a real-time step flow chart of the method of the present invention.

FIG. 2 is a schematic diagram showing the connection of various modules of the system of the present invention.

DETAILED DESCRIPTION

The above contents in combination with the implementation of the present invention are merely examples and explanations of the concept of the present invention. Technical passengers in this technical field may make various modifications or additions to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the concept of the invention or exceed the scope defined by the claims, they shall all fall within the protection scope of the present invention.

Please refer to Figure 1. The purpose of the present invention can be achieved through the following technical solutions: The first aspect of the present invention provides an energy-saving optimization control method for a screw air compressor station based on AI technology, the method comprising: S1. Collecting basic information of the target screw air compressor station, including the station layout diagram, historical environmental parameters, technical configuration parameters and historical operating parameters of each screw air compressor of the same type and model, building a simulation model of the target screw station and creating an operating condition simulation test scenario.

Specifically, the construction of the target screw station simulation model includes: the three-dimensional modeling software establishes the corresponding three-dimensional layout model through the station layout diagram of the target screw station, and configures and designs the corresponding sub-models of each screw air compressor in the three-dimensional layout model according to the design configuration parameters of each screw air compressor.

The historical environmental parameters of the target screw air compressor station are fitted, where the historical environmental parameters include the indoor temperature value, indoor humidity value and indoor and outdoor pressure difference of each unit time period in each historical working day of the season. The fitting functions corresponding to the indoor temperature, indoor humidity value and indoor and outdoor pressure difference of the target screw air compressor station per unit working day of the season are obtained respectively, and they are mapped to the three-dimensional layout model of the target screw air compressor station for environmental rendering processing.

It should be noted that the process of obtaining the fitting function corresponding to the indoor temperature, indoor humidity value, and indoor and outdoor pressure difference of the target screw air compressor station per working day in the season includes: constructing a rectangular coordinate system with time as the horizontal axis and temperature value as the vertical axis, wherein the horizontal axis coordinate unit span of the rectangular coordinate system is a unit time period, and importing the indoor temperature values of each unit time period in each historical working day of the target screw air compressor station in the season into the rectangular coordinate system to draw the indoor temperature change curve of the target screw air compressor station in the season, and further importing it into Matlab software to use its best fitting tool to obtain the global fitting function of the indoor temperature change of the target screw air compressor station in the season, which is used as the indoor temperature fitting function of the target screw air compressor station per working day in the season. Similarly, the fitting function corresponding to the indoor humidity value and indoor and outdoor pressure difference of the target screw air compressor station per working day in the season is obtained.

The three-dimensional layout model was preliminarily verified through the historical operating parameters of each screw air compressor, where the historical operating parameters include the suction pressure, air intake, exhaust pressure range, exhaust volume and motor power for each working period on each working day in the current season. Taking the suction pressure and exhaust pressure range for each working period on each working day in the current season as the starting point, the model parameters were iteratively adjusted until the intake volume, exhaust volume and motor power for each working period on each working day in the current season predicted by the model were consistent with the intake volume, exhaust volume and motor power for the corresponding period in the historical operating parameters at the preset values, thus completing the construction of the target screw station simulation model.

The embodiment of the present invention integrates the layout, environment, equipment configuration and historical operating data of the target screw air compressor station to achieve a comprehensive simulation of the overall operating status of the target screw air compressor station, which helps to more accurately map the energy efficiency performance of the screw air compressor under different working conditions and provide a basis for formulating optimized operating strategies.

Specifically, the creation of the working condition simulation test scenario includes: setting the exhaust pressure range, suction pressure, and cooling water inlet temperature of each screw air compressor to their corresponding unified preset values.

Each screw air compressor continuously provides a preset amount of compressed air within a preset time period as the working condition simulation test scenario 1, which is recorded as the same-condition multi-machine scenario.

The preset time period is divided into test periods with equal intervals, and the compressed air volume is progressively accumulated according to the time sequence of each test period to obtain the corresponding level of compressed air volume in each test period. Each screw air compressor continuously provides the corresponding level of compressed air volume in each test period as the second working condition simulation test scenario, which is recorded as the full-condition single-machine scenario.

The same-condition multi-machine scenario and the full-condition single-machine scenario are used together as working condition simulation test scenarios.

The embodiment of the present invention combines the multi-machine scenario with the full-condition single-machine scenario to create an operating condition simulation test scenario for the target screw air compressor station simulation model, which helps to more comprehensively and efficiently identify the abnormal energy consumption performance of the screw air compressor, and provides a scientific basis for screening the screw air compressors with abnormal energy consumption in the target screw air compressor station.

S2. Perform simulation tests on each screw air compressor in the target screw air compressor station according to the working condition simulation test scenario, and screen out each screw air compressor with abnormal energy consumption in the target screw air compressor station, which are recorded as abnormal air compressors.

Specifically, the screening of each screw air compressor with abnormal energy consumption in the target screw air compressor station includes: collecting the specific power of each screw air compressor at each monitoring time point within a preset time period for a scenario of multiple machines in the same condition; ,in is the number of each screw air compressor, , is the number of each monitoring time point in the preset time period, , obtain the benchmark specific power of the screw air compressor in the preset time period under the same condition of multiple machines through mean calculation , according to the formula Analyze the energy consumption abnormality evaluation coefficient of each screw air compressor in the same multi-machine scenario, among which The number of monitoring time points within the preset time period.

It should be noted that the acquisition of the specific power of each screw air compressor at each monitoring time point within the preset time period of the above-mentioned multi-machine scenario under the same condition and the average specific power of each screw air compressor in each test period of the subsequent single-machine scenario under all conditions are achieved through the virtual sensor network deployed in the simulation model of the target screw air compressor station. Virtual sensors are configured at the key monitoring points of each screw air compressor to realize continuous real-time monitoring of the output electric power and compressed gas flow, and transmit the collected data to the data processing unit of the simulation model for specific power calculation.

Collect the average specific power of each screw air compressor in each test period in the full single machine scenario ,in is the number of each test period, According to the type and model of each screw air compressor, the reasonable operating power ratio range of the screw air compressor of the same type and model specified by the screw air compressor manufacturer is extracted from the WEB cloud to obtain the reasonable reference power ratio of the screw air compressor in the full-case single-machine scenario. and reasonable deviation power .

It should be noted that the reasonable reference specific power of the screw air compressor in the above-mentioned full-condition single-machine scenario is obtained by averaging the upper and lower limits of the reasonable range of the operating specific power of the screw air compressors of the same type and model as specified by the screw air compressor manufacturer, and the reasonable deviation specific power of the screw air compressor in the full-condition single-machine scenario is obtained by calculating the absolute difference between the reasonable reference specific power of the screw air compressor in the full-condition single-machine scenario and the upper limit of the reasonable range of the operating specific power of the screw air compressors of the same type and model as specified by the screw air compressor manufacturer.

By formula Analyze the energy consumption abnormality evaluation coefficient of each screw air compressor in the full single machine scenario, among which is the number of test periods, For the full stand-alone scenario Screw air compressor The average specific power during the test period.

Will The comprehensive energy consumption anomaly coefficient of each screw air compressor is obtained by multiplying and adding up the corresponding preset weight proportions, and the screw air compressors whose comprehensive energy consumption anomaly coefficient is greater than the preset warning threshold are screened out as the energy consumption anomaly screw air compressors in the target screw air compressor station.

S3. Trace the causes of abnormal energy consumption of each abnormal air compressor.

Specifically, the cause of abnormal energy consumption of each abnormal air compressor is traced, including: collecting the loading times, unloading times, loading pressure values and unloading pressure values of each abnormal air compressor in each test period of the full single-machine scenario, and treating the loading times or unloading times of the abnormal air compressor in any test period exceeding the preset standard times as the control unit abnormality judgment condition 1.

It should be noted that the number of loading and unloading times, the number of loading and unloading pressure values, and the number of unloading pressure values of each abnormal air compressor in each test period of the above-mentioned full-condition single-machine scenario are collected by continuously monitoring the operating mode and real-time pressure values of the status monitoring virtual sensors deployed in each abnormal air compressor sub-model in the target screw station simulation model, where the operating mode includes loading mode and unloading mode.

The upper limit value of the unified preset exhaust pressure range of each abnormal air compressor is used as the unloading pressure threshold, and the lower limit value is used as the loading pressure threshold. Any loading pressure value less than the loading pressure threshold or any unloading pressure value greater than the unloading pressure threshold in any test period of the abnormal air compressor is regarded as the control unit abnormality judgment condition 2.

According to the compressed air volume corresponding to each test period and the loading performance curve and unloading performance curve of the screw air compressor of the same type and model specified by the screw air compressor manufacturer stored in the WEB cloud, obtain the reasonable loading pressure value and reasonable unloading pressure value corresponding to the compressed air volume corresponding to each test period, calculate the loading pressure deviation ratio and unloading pressure deviation ratio of each abnormal air compressor in each test period, and regard any loading pressure deviation ratio or any unloading pressure deviation ratio of the abnormal air compressor in any test period that is greater than the preset pressure deviation ratio threshold as the control unit abnormality judgment condition 3.

It should be noted that the calculation process of each loading pressure deviation ratio and each unloading pressure deviation ratio in each test period of each abnormal air compressor is as follows: the absolute deviation value of each loading pressure value in each test period of each abnormal air compressor is calculated with the reasonable loading pressure value in the corresponding period, and the ratio of the calculated absolute deviation value to the reasonable loading pressure value in the corresponding period is used as the loading pressure deviation ratio in each test period of each abnormal air compressor. Similarly, the absolute deviation value of each unloading pressure value in each test period of each abnormal air compressor is calculated with the reasonable unloading pressure value in the corresponding period, and the ratio of the calculated absolute deviation value to the reasonable unloading pressure value in the corresponding period is used as the unloading pressure deviation ratio in each test period of each abnormal air compressor.

If an abnormal air compressor in the full-case single-machine scenario meets any control unit abnormality judgment condition, the abnormal energy consumption cause of the abnormal air compressor is marked as control unit abnormality.

Specifically, the tracing of the causes of abnormal energy consumption of each abnormal air compressor also includes: collecting the maximum lubricating oil temperature value, the maximum motor temperature value, and the flow rate of the heat exchange medium of each abnormal air compressor within a preset period of time in the same multi-machine scenario; And the inlet and outlet temperature difference ,in is the number of each abnormal air compressor, .

If the maximum lubricating oil temperature value of an abnormal air compressor exceeds the preset screw air compressor lubricating oil safety temperature threshold or the maximum motor temperature value exceeds the preset screw air compressor motor safety temperature threshold within the preset time period of the same multi-machine scenario, the abnormal energy consumption cause of the abnormal air compressor is marked as cooling unit abnormality.

Calculate the heat recovery efficiency of each abnormal air compressor within a preset time period in the same multi-machine scenario If the heat recovery efficiency of one of the abnormal air compressors is less than a preset reasonable threshold value of heat recovery efficiency, the abnormal energy consumption cause of the abnormal air compressor is marked as a heat recovery unit abnormality.

It should be noted that if analysis shows that the cause of abnormal energy consumption of an abnormal air compressor cannot be attributed to any of the abnormal control unit, cooling unit or heat recovery unit, the cause of abnormal energy consumption of the abnormal air compressor will be marked as other, and the advanced notification process will be triggered to send an emergency energy consumption abnormality warning notification in the form of a text message to the authorized management personnel of the target screw air compressor station, prompting manual detection of the cause of abnormal energy consumption and taking corrective measures.

Specifically, the The calculation formula is: ,in are respectively the preset density and preset specific heat capacity of the heat exchange medium, The duration corresponding to the preset time period.

S4. Develop optimization strategies for the causes of abnormal energy consumption of each abnormal air compressor, so as to improve each abnormal air compressor.

Specifically, the optimization strategy for each abnormal cause of abnormal energy consumption of the abnormal air compressor includes: if the abnormal cause of the abnormal energy consumption of the abnormal air compressor is the abnormal control unit, determining whether the abnormal air compressor control unit abnormality meets the judgment conditions, if it meets the judgment condition 1, increasing the proportional coefficient of the PID controller by a preset unit control value, if it meets the judgment condition 2, increasing the differential coefficient of the PID controller by a preset unit control value, and if it meets the judgment condition 3, increasing the integral coefficient of the PID controller by a preset unit control value.

It should be noted that the basis for determining that the abnormal air compressor control unit abnormally meets the judgment conditions to adjust the relevant parameters of the PID controller of the abnormal air compressor is: monitoring whether the number of loading or unloading times during the abnormal air compressor test period exceeds the preset standard times, which directly reflects whether the control unit frequently switches between loading and unloading states. It may be due to the inaccurate adjustment of the proportional link of the PID controller, resulting in the abnormal air compressor responding too sensitively or slowly. Therefore, when the judgment condition 1 is met, the proportional coefficient of the PID controller is adjusted to increase the preset unit control value, aiming to improve the accuracy of the control response and reduce unnecessary loading and unloading cycles.

Check whether the loading pressure and unloading pressure during the abnormal air compressor test period exceed the uniform preset exhaust pressure range. This involves the stability and accuracy of pressure control, which is usually related to the differential link of the PID controller, because the differential action can respond to pressure changes in advance and reduce overshoot. When judgment condition 2 is met, it indicates that the control unit's prediction and response to pressure changes are insufficient. At this time, increasing the differential coefficient preset unit control value helps to enhance the system's ability to quickly suppress pressure fluctuations.

Check if the loading pressure deviation ratio or unloading pressure deviation ratio during the abnormal air compressor test period is greater than the preset pressure deviation ratio threshold, which involves the steady-state problem of the PID controller. When the judgment condition 3 is met, it indicates that the cumulative effect of the control unit PID controller in the integral link has failed to effectively eliminate the steady-state error. Increasing the preset unit control value of the integral coefficient can help gradually eliminate the static deviation and improve long-term stability.

If the abnormal air compressor energy consumption is caused by abnormal cooling unit, increase the opening and closing degree of the abnormal air compressor cooling water pump valve by one gear.

If the abnormal air compressor energy consumption is caused by an abnormal heat recovery unit, the opening degree of the abnormal air compressor heat recovery circulation pump valve will be increased by one level.

Based on this, optimization strategies can be formulated for the abnormal causes of energy consumption of each air compressor.

The embodiment of the present invention traces the causes of abnormal energy consumption of each abnormal air compressor from three dimensions: control unit abnormality, cooling unit abnormality and heat recovery unit abnormality, and formulates targeted and personalized optimization strategies based on the traced causes of abnormal energy consumption, thereby avoiding the limitations and defects of energy-saving optimization measures in a single loading and unloading control dimension during the operation of screw air compressors in the prior art. It not only helps solve the problem of abnormal energy consumption of screw air compressors, but also promotes a significant improvement in the overall energy efficiency and management level of screw air compressor stations.

S5. Re-run simulation tests on each abnormal air compressor after improvement, evaluate the energy-saving optimization effect of each abnormal air compressor and provide feedback.

Specifically, the energy-saving optimization effect of each abnormal air compressor is evaluated, including: analyzing the energy consumption abnormality evaluation coefficients of each abnormal air compressor after improvement for the same condition multi-machine scenario and the full condition single machine scenario when re-simulating and testing, recorded as , calculate the energy-saving optimization coefficient of each abnormal air compressor , , which is used as the evaluation index of energy-saving optimization effect of each abnormal air compressor. They are the extracted multi-machine scenario with the same condition and the single-machine scenario with all conditions. The energy consumption abnormality evaluation coefficient of an abnormal air compressor.

The embodiment of the present invention re-simulates and tests each abnormal air compressor after improvement, evaluates the energy-saving optimization effect of each abnormal air compressor and provides feedback, so as to prompt professional staff to further adjust the optimization strategy according to the evaluation results, form a closed loop of continuous improvement, and continuously improve the energy efficiency level of the air compressor.

Please refer to Figure 2. The second aspect of the present invention provides an energy-saving optimization control system for a screw air compressor station based on AI technology, including: a simulation model building module, an energy consumption anomaly screening module, an energy consumption anomaly tracing module, an optimization strategy formulation module, an energy-saving effectiveness evaluation module and a cloud database.

The simulation model building module is connected to the energy consumption anomaly screening module, the energy consumption anomaly screening module is connected to the energy consumption anomaly tracing module, the energy consumption anomaly tracing module is connected to the optimization strategy formulation module, the optimization strategy formulation module is connected to the energy-saving effectiveness evaluation module, and the cloud database is respectively connected to the energy consumption anomaly screening module and the energy consumption anomaly tracing module.

The simulation model building module is used to collect the basic information of the target screw air compressor station, including the station layout, historical environmental parameters, technical configuration parameters and historical operating parameters of each screw air compressor of the same type and model, build a simulation model of the target screw station and create operating simulation test scenarios.

The energy consumption anomaly screening module is used to perform simulation tests on the target screw air compressor station according to the operating condition simulation test scenario, and screen the screw air compressors with abnormal energy consumption in the target screw air compressor station, which are recorded as abnormal air compressors.

The energy consumption abnormality tracing module is used to trace the causes of abnormal energy consumption of each abnormal air compressor.

The optimization strategy formulation module is used to formulate optimization strategies for the abnormal causes of energy consumption of each abnormal air compressor, so as to improve each abnormal air compressor.

The energy-saving effectiveness evaluation module is used to re-simulate and test each abnormal air compressor after improvement, evaluate the energy-saving optimization effect of each abnormal air compressor and provide feedback.

The cloud database is used to store the reasonable operating power ratio range, loading performance curve and unloading performance curve of various types and models of screw air compressors specified by screw air compressor manufacturers.

The above contents are merely examples and explanations of the concept of the present invention. Technical passengers in the technical field may make various modifications or additions to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the concept of the invention or exceed the scope defined by the claims, they should all fall within the protection scope of the present invention.

Claims (10)

1. The energy-saving optimization control method for the screw air compression station room based on the AI technology is characterized by comprising the following steps:

s1, collecting basic information of a target screw rod air compression station room, wherein the basic information comprises a station room layout chart, historical environment parameters, technical configuration parameters and historical operation parameters of screw rod air compressors with the same type and model, constructing a target screw rod station room simulation model and creating a working condition simulation test scene;

S2, performing simulation test on each screw air compressor in the target screw air compression station room according to the working condition simulation test scene, screening each abnormal energy consumption screw air compressor in the target screw air compression station room, and marking the abnormal air compressors;

s3, tracing the energy consumption abnormal cause of each abnormal air compressor;

S4, an optimization strategy aiming at the energy consumption abnormality cause of each abnormal air compressor is formulated, so that each abnormal air compressor is improved;

s5, carrying out simulation test again on each abnormal air compressor after the improvement is completed, evaluating energy-saving optimization effect of each abnormal air compressor and feeding back.

2. The energy-saving optimization control method for the screw air compression station room based on the AI technology as set forth in claim 1, wherein the method comprises the following steps: the building of the target screw station room simulation model comprises the following steps: the three-dimensional modeling software establishes a corresponding three-dimensional layout model through a station room layout diagram of a target screw station room, and carries out configuration design on corresponding sub-models of all screw air compressors in the three-dimensional layout model according to design configuration parameters of all screw air compressors;

Fitting historical environmental parameters of the target screw rod air compression station room, wherein the historical environmental parameters comprise indoor temperature values, indoor humidity values and indoor and outdoor pressure differences of each unit time period in each working day of the season history, respectively acquiring fitting functions corresponding to the indoor temperature, the indoor humidity values and the indoor and outdoor pressure differences of the unit working day of the target screw rod air compression station room in the season, mapping the fitting functions to a three-dimensional layout model of the target screw rod air compression station room, and performing environmental rendering treatment;

And carrying out preliminary verification on the three-dimensional layout model through historical operation parameters of each screw air compressor, wherein the historical operation parameters comprise suction pressure, air inflow, exhaust pressure interval, exhaust amount and motor power of each working period in each working day of the history of the season, and iteratively adjusting the model parameters by taking the suction pressure and the exhaust pressure interval of each working period in each working day of the history of the season as cut-in points until the model predicts that the coincidence degree of the air inflow, the exhaust amount and the motor power of each working period in each working day of the history of the season and the air inflow, the exhaust amount and the motor power of the corresponding period in the historical operation parameters reaches preset values, thereby completing the building of the simulation model of the target screw station room.

3. The energy-saving optimization control method for the screw air compression station room based on the AI technology as set forth in claim 1, wherein the method comprises the following steps: the creating the working condition simulation test scene comprises the following steps: respectively setting the exhaust pressure interval, the suction pressure and the inflow temperature and the inflow rate of cooling water of each screw air compressor to corresponding unified preset values;

Continuously providing a preset compressed air quantity for each screw air compressor in a preset time period to serve as a working condition simulation test scene I, and recording the working condition simulation test scene I as a same-condition multi-machine scene;

Dividing a preset time period into test time periods according to equal interval time length, accumulating compressed air in steps according to the time sequence of the test time periods, obtaining the corresponding cascade compressed air of the test time periods, continuously providing the corresponding cascade compressed air of each screw air compressor in the test time periods as a working condition simulation test scene II, and recording the working condition simulation test scene II as a full-condition single machine scene;

And the same-condition multi-machine scene and the full-condition single-machine scene are used as working condition simulation test scenes together.

4. The energy-saving optimization control method for the screw air compression station room based on the AI technology as set forth in claim 3, wherein the energy-saving optimization control method is characterized in that: each abnormal energy consumption screw air compressor in the screening target screw air compression station room comprises: specific power of each monitoring time point of each screw air compressor in preset time period of same-condition multi-machine scene is collectedWhereinThe serial numbers of the air compressors of the screws are given,，For the number of each monitoring time point in the preset time period,Obtaining reference specific power of the screw air compressor in the same-condition multi-machine scene preset time period through mean value calculationFrom the formulaAnalyzing abnormal energy consumption evaluation coefficients of all screw air compressors in the same-condition multi-machine scene, whereinMonitoring the number of time points in a preset time period;

The average specific power of each screw air compressor in each test period of all-condition single machine scene is collected WhereinFor the number of each test period,According to the types and the models of the screw air compressors, extracting the reasonable operation specific power interval of the screw air compressors of the same type and the same type standardized by the screw air compressor manufacturer from the WEB cloud end, and obtaining the reasonable reference specific power of the all-condition single-machine scene screw air compressorAnd reasonable deviation ratio power；

From the formulaAnalyzing abnormal energy consumption evaluation coefficients of all-condition single-machine scenes of all-screw air compressors, whereinIn order to test the number of time periods,Is the full-condition single machine sceneFirst screw air compressorAverage specific power over each test period;

Will be And respectively accumulating the products of the energy consumption abnormal coefficients and the corresponding preset weight duty ratio to obtain the comprehensive energy consumption abnormal coefficients of the screw air compressors, and screening the screw air compressors with the comprehensive energy consumption abnormal coefficients larger than the preset warning threshold value as the abnormal energy consumption screw air compressors in the target screw air compression station room.

5. The energy-saving optimization control method for the screw air compression station room based on the AI technology as set forth in claim 4, wherein: the tracing of the energy consumption abnormal cause of each abnormal air compressor comprises the following steps: collecting the loading times, unloading times, loading pressure values and unloading pressure values of each abnormal air compressor in each test period of the all-condition single machine scene, and taking the times that the loading times or the unloading times of any test period of the abnormal air compressor exceed the preset standard times as the abnormal judgment condition 1 of the control unit;

Taking the upper limit value and the lower limit value of a unified preset exhaust pressure interval of each abnormal air compressor as an unloading pressure threshold value and a loading pressure threshold value, and taking any loading pressure value smaller than the loading pressure threshold value or any unloading pressure value larger than the unloading pressure threshold value in any test period of the abnormal air compressors as a control unit abnormal judgment condition 2;

According to the corresponding cascade compressed air quantity of each test period and the standard loading performance curve graph and unloading performance curve graph of the screw air compressor with the same type of screw air compressor manufactured by the WEB cloud end, reasonable loading pressure values and reasonable unloading pressure values corresponding to the corresponding cascade compressed air quantity of each test period are obtained, each loading pressure deviation ratio and each unloading pressure deviation ratio in each test period of each abnormal air compressor are calculated, and any loading pressure deviation ratio or any unloading pressure deviation ratio in any test period of the abnormal air compressor is regarded as a control unit abnormality judgment condition 3;

if a certain abnormal air compressor in the all-condition single machine scene meets any control unit abnormal judgment condition, marking the abnormal energy consumption cause of the abnormal air compressor as the abnormal control unit.

6. The energy-saving optimization control method for the screw air compression station room based on the AI technology as set forth in claim 5, wherein the energy-saving optimization control method is characterized in that: the tracing of the energy consumption abnormal cause of each abnormal air compressor further comprises: collecting the maximum lubricating oil temperature value, the maximum motor temperature value and the flow of heat exchange medium of each abnormal air compressor in the preset period of the same-condition multi-machine sceneAnd inlet-outlet temperature difference valueWhereinIs the number of each abnormal air compressor,；

If the maximum lubricating oil temperature value of an abnormal air compressor exceeds the preset screw air compressor lubricating oil safety temperature threshold value or the maximum motor temperature value exceeds the preset screw air compressor motor safety temperature threshold value in the same-condition multi-machine scene preset period, marking the abnormal energy consumption of the abnormal air compressor as abnormal cooling unit;

calculating heat recovery efficiency of each abnormal air compressor in preset time period of same-condition multi-machine scene If the heat recovery efficiency of one abnormal air compressor is smaller than the preset reasonable heat recovery efficiency threshold, marking the abnormal energy consumption of the abnormal air compressor as abnormal heat recovery unit.

7. The energy-saving optimization control method for the screw air compression station room based on the AI technology as set forth in claim 6, wherein: the saidThe calculation formula of (2) is as follows: Wherein Respectively the preset density and the preset specific heat capacity of the heat exchange medium,The preset time period corresponds to the duration.

8. The energy-saving optimization control method for the screw air compression station room based on the AI technology as set forth in claim 6, wherein: the making of the optimization strategy aiming at the energy consumption abnormality reason of each abnormal air compressor comprises the following steps: if the energy consumption abnormality of the abnormal air compressor is caused by abnormality of the control unit, determining that the abnormality of the control unit of the abnormal air compressor meets the judgment condition, if the abnormality meets the judgment condition 1, adding a preset unit regulation value to the proportional coefficient of the PID controller, if the abnormality meets the judgment condition 2, adding a preset unit regulation value to the differential coefficient of the PID controller, and if the abnormality meets the judgment condition 3, adding a preset unit regulation value to the integral coefficient of the PID controller;

if the energy consumption abnormality of the abnormal air compressor is caused by abnormality of the cooling unit, the opening and closing degree of a valve of a cooling water pump of the abnormal air compressor is increased by one gear;

if the energy consumption abnormality of the abnormal air compressor is caused by abnormality of the heat recovery unit, the opening and closing degree of a valve of a heat recovery circulating pump of the abnormal air compressor is increased by one gear;

and thus, an optimization strategy aiming at the energy consumption abnormality cause of each abnormal air compressor is formulated.

9. The energy-saving optimization control method for the screw air compression station room based on the AI technology as set forth in claim 6, wherein: the evaluation of energy-saving optimization results of each abnormal air compressor comprises the following steps: when the simulation test is carried out again on each abnormal air compressor after the analysis and improvement, the energy consumption abnormal evaluation coefficients respectively aiming at the same-condition multi-machine situation and the full-condition single-machine situation are recorded asCalculating energy-saving optimization coefficients of abnormal air compressors，The evaluation index of energy-saving optimization effect of each abnormal air compressor is used as the evaluation index of energy-saving optimization effect of each abnormal air compressor, whereinThe extracted same-condition multi-machine scene and all-condition single-machine scene are respectively the firstAbnormal evaluation coefficients of energy consumption of the abnormal air compressors.

10. An AI technology-based energy-saving optimization control system for a screw air compression station room is characterized by comprising the following components:

The simulation model building module is used for collecting basic information of a target screw air compression station room, and comprises a station room layout chart, historical environment parameters, technical configuration parameters and historical operation parameters of screw air compressors with the same type and model, building a target screw station room simulation model and building a working condition simulation test scene;

The energy consumption abnormality screening module is used for carrying out simulation test on the target screw rod air compression station room according to the working condition simulation test scene, and screening each energy consumption abnormality screw rod air compressor in the target screw rod air compression station room, and recording the abnormal screw rod air compressors as each abnormal air compressor;

The energy consumption anomaly tracing module is used for tracing the energy consumption anomaly cause of each anomaly air compressor;

the optimization strategy making module is used for making an optimization strategy aiming at the energy consumption abnormality cause of each abnormal air compressor so as to improve each abnormal air compressor;

the energy-saving effect evaluation module is used for carrying out simulation test again on each improved abnormal air compressor, evaluating the energy-saving optimization effect of each abnormal air compressor and feeding back;

The cloud database is used for storing the reasonable running specific power interval, the loading performance curve graph and the unloading performance curve graph of the screw air compressors of various types and types specified by the screw air compressor manufacturer.