IOE-based water chilling unit AI group control virtual-real interaction display system and method

Abstract

The invention discloses a water chilling unit AI group control virtual-real interactive display system and method based on IOE, relates to the technical field of water chilling units, solves the problem that comprehensive energy consumption is not fully considered when an original unit is controlled, and achieves the lowest energy consumption by determining operation parameters of each unit based on cooling characteristics and quantitative polygons; after the cooling requirement is confirmed, the optimal operation process is locked by comparing the areas of the feature polygons, and the comprehensive energy consumption is minimized while it is ensured that each unit meets the cooling requirement; for example, after the cooling characteristics are determined, the combination with the lowest energy consumption is selected by calculating and comparing the polygonal areas under different operation parameter combinations, so that the energy utilization efficiency is greatly improved, and the operation cost of the water chilling unit is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of chillers, and in particular to an IOE-based chiller AI group control virtual-reality interactive display system and method. Background Art

[0002] In modern architecture and industrial production, chillers, as essential refrigeration equipment, are widely used in air conditioning systems, industrial cooling, and other scenarios. With the increasing demand for energy conservation and emission reduction, coupled with the trend toward intelligent equipment management, the drawbacks of traditional chiller group control systems are becoming increasingly prominent.

[0003] When it comes to energy management, traditional systems lack in-depth analysis of individual unit energy consumption characteristics, making it difficult to implement precise control measures tailored to different operating conditions. They typically employ fixed control strategies, failing to optimize unit operating parameters in real time based on actual load fluctuations. This leads to significant energy waste and high operating costs. Furthermore, the lack of effective mining and utilization of historical operating data makes it impossible to establish accurate energy consumption models, making it difficult to accurately predict and control energy consumption.

[0004] In terms of operation and control strategies, traditional methods often ignore the synergistic effects between different operating equipment and fail to comprehensively consider thermal characteristics and cooling needs. This causes the unit to either fail to meet cooling requirements during operation, affecting the normal operation of the system, or over-cool, resulting in energy waste. At the same time, unreasonable control strategies will also lead to frequent start-up and shutdown of equipment, uneven load, accelerated equipment wear, and reduced equipment service life. Summary of the Invention

[0005] In response to the shortcomings of the existing technology, the present invention provides an IOE-based chiller AI group control virtual-reality interactive display system and method, which solves the problem that the original unit does not fully consider the comprehensive energy consumption during control.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: a chiller AI group control virtual and real interactive display method based on IOE, comprising the following steps:

[0007] Step 1: Confirm the individual units associated with the chiller, and then confirm the energy consumption characteristic sequence associated with the individual units based on the historical operation data of the individual units. The specific sub-steps are:

[0008] Randomly select a unit from the chiller group as a selected unit, and determine the historical operating data associated with the selected unit during past operations;

[0009] Confirm the energy consumption parameters associated with different operating parameters per unit time from historical operating data, and average several groups of energy consumption parameters associated with the same operating parameters to confirm the average energy consumption associated with the corresponding operating parameters;

[0010] Sort the operating parameters associated with the selected units in ascending order of value to confirm the operating parameter sequence, and then sort several groups of average energy consumption according to the average energy consumption associated with the corresponding operating parameters to confirm the energy consumption characteristic sequence;

[0011] Step 2: Based on the energy consumption characteristic sequences associated with different units in this chiller, construct characteristic polygons, quantize the values within the energy consumption characteristic sequences, and generate quantized polygons belonging to this chiller based on the quantized values. The specific sub-steps are:

[0012] Determine the total number of individual units in the chiller and record it as G. Generate G equilateral lines. Then connect the end points of adjacent equilateral lines to generate a quantized polygon belonging to this chiller. The starting point of each equilateral line is the same, and the G equilateral lines are arranged in a circular array according to the starting point.

[0013] Associate each equilateral line within the quantized polygon with a group of selected units. Then, based on the selected units, determine the associated operating parameter sequence. The maximum operating parameter within this operating parameter sequence is used as the maximum measurement value of the corresponding equilateral line. The equilateral line is then scaled so that each scale is associated with a different operating parameter. Based on the determined energy consumption characteristic sequence, the mean energy consumption associated with each scale on the corresponding equilateral line is locked.

[0014] Step 3: Confirm the heat characteristics generated by the corresponding operating items of the running equipment. Based on the confirmed heat characteristics, lock the cooling characteristics. Then, based on the cooling characteristics and the quantified polygon, confirm the operating parameters of each unit and execute them. The specific method is as follows:

[0015] Confirm the operation items associated with the operation equipment, and then confirm the operation parameters of the corresponding operation items based on the confirmed operation items, and calibrate the operation parameters associated with different operation items as Y i , where i represents different running items;

[0016] Use: R i =Y i ×C i Confirm the heat signature R associated with the corresponding operation item i , where C i is the preset fixed coefficient factor associated with the corresponding operation item, and then the multiple groups of heat characteristics R iPerform mean processing and lock the characteristic heat, using: characteristic heat × F1 = cooling characteristics, where F1 is the preset coefficient factor;

[0017] Based on the confirmed cooling characteristics and the total number of units G in the chiller, the following formula is used: Cooling characteristics ÷ G = average characteristics. The scale of the average characteristics is confirmed on each equilateral line in the quantization polygon. The scale is recorded as the characteristic scale. The characteristic scales on adjacent equilateral lines are connected to confirm a set of characteristic polygons. The area of this characteristic polygon is recorded as M1.

[0018] Execute several translation processing processes: move the characteristic scale on the corresponding equilateral line, and in each movement process, the sum of the operating parameters associated with different characteristic scales is consistent with the cooling characteristics, and connect the adjacent characteristic scales in each movement process, confirm the characteristic polygon associated with the corresponding movement process, and simultaneously record the area of the confirmed characteristic polygon as M k , where k represents the characteristic polygons associated with different movement processes;

[0019] Will satisfy: M k The moving process of <M1 is recorded as a pending process, and the minimum area is selected from the determined pending processes: the area M associated with the pending process is selected. k In the k min, mark the pending process as the optimal process, determine the operating parameters associated with different equilateral lines in the optimal process, and control the corresponding unit to perform parameter execution based on the determined operating parameters;

[0020] Also includes:

[0021] Step 4: Based on the actual energy consumption and virtual energy consumption associated with the chiller, determine the energy consumption difference, and then determine and output a correction signal based on the corresponding energy consumption difference. The specific method is as follows:

[0022] Based on the confirmed best process, the average energy consumption associated with the operating parameters corresponding to the best process is locked, and several groups of average energy consumption are summed to lock the virtual energy consumption;

[0023] Then, in the actual operation process, for the specific energy consumption generated by a single unit in the chiller per unit time, several specific energy consumptions are summed up to lock the actual energy consumption;

[0024] Evaluate whether the virtual energy consumption and actual energy consumption meet the following conditions: |virtual energy consumption - actual energy consumption|≤Y1, where Y1 is a preset value. If so, no processing signal needs to be generated. If not, a correction signal is generated for display.

[0025] Preferably, an IOE-based chiller AI group control virtual-reality interactive display system includes:

[0026] The characteristic sequence confirmation end confirms the individual units associated with the chiller, and then confirms the energy consumption characteristic sequence associated with the individual units based on the historical operation data of the individual units;

[0027] The polygon confirmation end constructs characteristic polygons based on the energy consumption characteristic sequences associated with different units in the chiller, quantizes the values within the energy consumption characteristic sequences, and generates quantized polygons belonging to the chiller based on the quantized values;

[0028] The optimization parameter execution end confirms the heat characteristics generated by the corresponding operating items of the running equipment, locks the cooling characteristics based on the confirmed heat characteristics, and then confirms and executes the operating parameters of each unit based on the cooling characteristics and quantified polygons.

[0029] The present invention provides an IOE-based chiller AI group control virtual-reality interactive display system and method. Compared with the existing technology, it has the following advantages:

[0030] The present invention determines the operating parameters of each unit based on cooling characteristics and quantified polygons to achieve the lowest energy consumption. After confirming the cooling demand, the optimal operating process is determined by comparing the areas of the characteristic polygons, ensuring that each unit minimizes the overall energy consumption while meeting the cooling requirements. For example, after the cooling characteristics are determined, the polygon areas under different operating parameter combinations are calculated and compared to select the combination with the lowest energy consumption, greatly improving energy utilization efficiency and reducing the operating costs of the chiller.

[0031] By comparing actual and virtual energy consumption, anomalies in system operation can be promptly identified. When the deviation between actual and virtual energy consumption exceeds a preset value, a correction signal is generated, prompting staff to verify the historical data of the energy consumption characteristic sequence. This real-time monitoring and feedback mechanism helps to promptly identify and resolve potential problems in system operation, ensuring stable system operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 Schematic diagram of the process of the present invention;

[0033] Figure 2 It is a schematic diagram of the principle framework of the present invention. DETAILED DESCRIPTION

[0034] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0035] First embodiment

[0036] See also Figure 1 , this application provides an IOE-based chiller AI group control virtual-reality interactive display method, including the following steps:

[0037] Step 1: Confirm the individual units associated with the chiller, and then confirm the energy consumption characteristic sequence associated with the individual units based on the historical operation data of the individual units. Specifically, in the corresponding historical operation data, the units are associated with different energy consumption parameters under different operating parameter states. Based on a large amount of historical data, the corresponding parameters are averaged and the most accurate energy consumption characteristics are determined. The specific sub-steps for confirmation are:

[0038] Randomly select a unit from the chiller group as a selected unit, and determine the historical operating data associated with the selected unit during past operations;

[0039] Confirm the energy consumption parameters associated with different operating parameters per unit time from historical operating data, and average several groups of energy consumption parameters associated with the same operating parameters to confirm the average energy consumption associated with the corresponding operating parameters;

[0040] Sort the operating parameters associated with the selected units in ascending order of value to confirm the operating parameter sequence, and then sort several groups of average energy consumption according to the average energy consumption associated with the corresponding operating parameters to confirm the energy consumption characteristic sequence;

[0041] Specifically, during the operation of the corresponding selected unit, there are corresponding operating parameters and energy consumption parameters to facilitate subsequent numerical confirmation and selection process.

[0042] Step 2: Based on the energy consumption characteristic sequence associated with different units in this chiller, construct a characteristic polygon, quantize the values within the energy consumption characteristic sequence, and generate a quantized polygon belonging to this chiller based on the quantized value. Specifically, the number of sides of the quantized polygon corresponds to the total number of units within the corresponding chiller, and there are multiple quantized lines within the corresponding quantized polygon. Although the measurement quantization of each quantized line is inconsistent, their overall length is consistent, which facilitates subsequent feature confirmation and selects the optimal characteristic value. The specific sub-steps for generating the quantized polygon are:

[0043] Determine the total number of individual units in the chiller and record it as G. Generate G equilateral lines. The starting point of each equilateral line is the same. The G equilateral lines are arranged in a circular array based on the starting point. Then, connect the end points of adjacent equilateral lines to generate a quantized polygon belonging to this chiller.

[0044] Associate each equilateral line within the quantified polygon with a group of selected units, then confirm the associated operating parameter sequence based on the selected units, use the maximum operating parameter within this operating parameter sequence as the maximum measured value of the corresponding equilateral line, and scale the equilateral line so that each equally divided scale is associated with a different operating parameter, and again lock the mean energy consumption associated with each scale on the corresponding equally divided line based on the confirmed energy consumption characteristic sequence. Specifically, different operating parameters are associated with different mean energy consumptions. In this way, the corresponding mean energy consumption can be locked on the specific scale associated with the operating parameter, and relevant processing can be performed to assign a specific value to each scale.

[0045] Step 3: Confirm the heat characteristics generated by the corresponding operating items of the running equipment. Based on the confirmed heat characteristics, lock the cooling characteristics. Then, based on the cooling characteristics and the quantified polygons, confirm the operating parameters of each unit and execute them. Specifically, this method can effectively keep each unit in an operating state, and at the same time, the entire chiller can be in a state with the lowest energy consumption and achieve the corresponding water cooling effect, thereby achieving better operation control processing effects.

[0046] The specific method for confirming the corresponding operating parameters of each unit is as follows:

[0047] Confirm the operation items associated with the operation equipment, and then confirm the operation parameters of the corresponding operation items based on the confirmed operation items, and calibrate the operation parameters associated with different operation items as Y i , where i represents different running items;

[0048] Use: R i =Y i ×C i Confirm the heat signature R associated with the corresponding operation item i , where C i It is the preset fixed coefficient factor associated with the corresponding operation item. Its specific value is determined by the operator based on experience. Different operation items correspond to different fixed coefficient factors. Then the multiple groups of heat characteristics R i Perform mean value processing and lock the characteristic heat. Use the formula: characteristic heat × F1 = cooling characteristic, where F1 is a preset coefficient factor. Its specific value is determined by the operator based on experience. It is generally 1. The F1 value varies for different operating equipment.

[0049] Based on the confirmed cooling characteristics and the total number of units G in the chiller, the following formula is used: Cooling characteristics ÷ G = average characteristics. The scale of the average characteristics is confirmed on each equilateral line in the quantization polygon. The scale is recorded as the characteristic scale. The characteristic scales on adjacent equilateral lines are connected to confirm a set of characteristic polygons. The area of this characteristic polygon is recorded as M1.

[0050] Execute several translation processing processes: move the characteristic scale on the corresponding equilateral line, and in each movement process, the sum of the operating parameters associated with different characteristic scales is consistent with the cooling characteristics, and connect the adjacent characteristic scales in each movement process, confirm the characteristic polygon associated with the corresponding movement process, and simultaneously record the area of the confirmed characteristic polygon as M k , where k represents the characteristic polygons associated with different movement processes;

[0051] Will satisfy: M k The moving process of <M1 is recorded as a pending process, and the minimum area is selected from the determined pending processes: the area M associated with the pending process is selected. k In the k min (that is, the corresponding process associated with the minimum area value), calibrate this pending process as the optimal process, and determine the operating parameters associated with different equilateral lines in the optimal process, and control the corresponding units to execute parameters based on the determined operating parameters (different selected units in the chiller need to execute different operating parameters, and the resulting cooling intensity is also different). Specifically, according to this processing method, not only can the corresponding chiller be guaranteed to achieve the corresponding cooling process, but the comprehensive energy consumption of each unit can also be minimized, achieving a better energy consumption optimization process, thereby achieving the best AI group control effect;

[0052] For example: the proposed cooling characteristic is 40, and there are four single units in the chiller. Then the average characteristic confirmed for each single unit is 10. The operating parameter characteristic associated with the corresponding average characteristic 10 is confirmed on the bisector of the corresponding polygon, thereby locking the corresponding characteristic scale, and then controlling the corresponding characteristic scale to move on the corresponding bisector. When the value of a certain bisector moves from top to bottom, the associated heat value will also become smaller, and the value associated with another set of bisectors needs to move from bottom to top. Then, based on the corresponding comprehensive movement process, the polygon area associated with each movement process is confirmed. When the corresponding polygon area is at the minimum value, the optimal determination method can be locked. Subsequent cooling based on this optimal determination method can achieve the optimal cooling effect and simultaneously achieve the optimal energy consumption solution.

[0053] Step 4: Based on the actual energy consumption and virtual energy consumption associated with the chiller, determine the energy consumption difference, and then determine and output a correction signal based on the corresponding energy consumption difference. The specific method of determining the correction signal is:

[0054] Based on the confirmed best process, the average energy consumption associated with the operating parameters corresponding to the best process is locked, and several groups of average energy consumption are summed to lock the virtual energy consumption;

[0055] Then, in the actual operation process, for the specific energy consumption generated by a single unit in the chiller per unit time, several specific energy consumptions are summed up to lock the actual energy consumption;

[0056] Evaluate whether the virtual energy consumption and actual energy consumption meet the following criteria: |virtual energy consumption - actual energy consumption|≤Y1, where Y1 is a preset value, and its specific value is determined by the operator based on experience. If it meets the criteria, no processing signal needs to be generated, indicating that the virtual-real interaction meets the criteria. If it does not meet the criteria, a correction signal is generated for display. Based on this correction signal, external personnel re-verify the historical operating data used in the confirmation process of the energy consumption feature sequence, and perform feature analysis again based on the corresponding verification process to lock in the optimal feature analysis effect.

[0057] Second embodiment

[0058] An IOE-based chiller AI group control virtual-reality interactive display system, including:

[0059] The characteristic sequence confirmation end confirms the individual units associated with the chiller, and then confirms the energy consumption characteristic sequence associated with the individual units based on the historical operation data of the individual units;

[0060] The polygon confirmation end constructs characteristic polygons based on the energy consumption characteristic sequences associated with different units in the chiller, quantizes the values within the energy consumption characteristic sequences, and generates quantized polygons belonging to the chiller based on the quantized values;

[0061] The optimization parameter execution end confirms the heat characteristics generated by the corresponding operating items of the running equipment, locks the cooling characteristics based on the confirmed heat characteristics, and then confirms and executes the operating parameters of each unit based on the cooling characteristics and quantified polygons.

[0062] Some of the data in the above formulas are dimensionless and numerically calculated. Meanwhile, the contents not described in detail in this specification belong to the prior art known to those skilled in the art.

[0063] The above embodiments are only used to illustrate the technical method of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A virtual-reality interactive display method for AI group control of chillers based on IOE, characterized in that: The following steps are involved: Step 1: Confirm the individual units associated with the chiller, and then confirm the energy consumption characteristic sequence associated with the individual units based on the historical operation data of the individual units; Step 2: Based on the energy consumption characteristic sequences associated with different units in the chiller, construct characteristic polygons, quantize the values within the energy consumption characteristic sequences, and generate quantized polygons belonging to the chiller based on the quantized values; Step 3: Confirm the heat characteristics generated by the corresponding operating items of the running equipment, lock the cooling characteristics based on the confirmed heat characteristics, and then confirm and execute the operating parameters of each unit based on the cooling characteristics and the quantified polygon.

2. The IOE-based chiller AI group control virtual-reality interactive display method according to claim 1 is characterized in that: In step 1, the specific sub-steps for confirming the energy consumption characteristic sequence are: Randomly select a unit from the chiller group as a selected unit, and determine the historical operating data associated with the selected unit during past operations; Confirm the energy consumption parameters associated with different operating parameters per unit time from historical operating data, and average several groups of energy consumption parameters associated with the same operating parameters to confirm the average energy consumption associated with the corresponding operating parameters; The operating parameters associated with the selected units are sorted according to the values from small to large to confirm the operating parameter sequence. Then, according to the mean energy consumption associated with the corresponding operating parameters, several groups of mean energy consumption are sorted to confirm the energy consumption characteristic sequence.

3. The IOE-based chiller AI group control virtual-reality interactive display method according to claim 1 is characterized in that: In step 2, the specific sub-steps of generating the quantized polygon corresponding to the chiller are: Determine the total number of individual units in the chiller and record it as G, then generate G equilateral lines, and then connect the end points of adjacent equilateral lines to generate a quantized polygon belonging to this chiller; Each equilateral line within the quantified polygon is associated with a group of selected units. Then, the associated operating parameter sequence is confirmed based on the selected units. The maximum operating parameter within this operating parameter sequence is used as the maximum measurement value of the corresponding equilateral line. The equilateral line is scaled so that each equally divided scale is associated with a different operating parameter. Then, based on the confirmed energy consumption characteristic sequence, the mean energy consumption associated with each scale on the corresponding equally divided line is locked.

4. The IOE-based chiller AI group control virtual-reality interactive display method according to claim 3 is characterized in that: The starting point of each equilateral line is the same, and the G equilateral lines are arranged in a circular array according to the starting point.

5. The IOE-based chiller AI group control virtual-reality interactive display method according to claim 1 is characterized in that: In step 3, the specific method for confirming the corresponding operating parameters of each unit is: Confirm the operation items associated with the operation equipment, and then confirm the operation parameters of the corresponding operation items based on the confirmed operation items, and calibrate the operation parameters associated with different operation items as Y i , where i represents different running items; Use: R i =Y i ×C i Confirm the heat signature R associated with the corresponding operation item i , where C i is the preset fixed coefficient factor associated with the corresponding operation item, and then the multiple groups of heat characteristics R i Perform mean processing, lock characteristic heat, and use : Characteristic heat × F1 = cooling characteristic, where F1 is the preset coefficient factor; Based on the confirmed cooling characteristics and the total number of units G in the chiller, the following formula is used: Cooling characteristics ÷ G = average characteristics. The scale of the average characteristics is confirmed on each equilateral line in the quantization polygon. The scale is recorded as the characteristic scale. The characteristic scales on adjacent equilateral lines are connected to confirm a set of characteristic polygons. The area of this characteristic polygon is recorded as M1. Execute several translation processing processes: move the characteristic scale on the corresponding equilateral line, and in each movement process, the sum of the operating parameters associated with different characteristic scales is consistent with the cooling characteristics, and connect the adjacent characteristic scales in each movement process, confirm the characteristic polygon associated with the corresponding movement process, and simultaneously record the area of the confirmed characteristic polygon as M k , where k represents the characteristic polygons associated with different movement processes; Will satisfy: M k The moving process of <M1 is recorded as a pending process, and the minimum area is selected from the determined pending processes: the area M associated with the pending process is selected. k In the k min, calibrate the pending process as the optimal process, determine the operating parameters associated with different equilateral lines in the optimal process, and control the corresponding unit to perform parameter execution based on the determined operating parameters.

6. The IOE-based chiller AI group control virtual-reality interactive display method according to claim 5 is characterized in that: Also includes: Step 4: Based on the actual energy consumption and virtual energy consumption associated with the chiller, determine the energy consumption difference, and then determine and output a correction signal based on the corresponding energy consumption difference.

7. The IOE-based chiller AI group control virtual-reality interactive display method according to claim 6 is characterized in that: In step 4, the specific method of confirming the correction signal is: Based on the confirmed best process, the average energy consumption associated with the operating parameters corresponding to the best process is locked, and several groups of average energy consumption are summed to lock the virtual energy consumption; Then, in the actual operation process, for the specific energy consumption generated by a single unit in the chiller per unit time, several specific energy consumptions are summed up to lock the actual energy consumption; Evaluate whether the virtual energy consumption and actual energy consumption meet the following conditions: |virtual energy consumption - actual energy consumption|≤Y1, where Y1 is a preset value. If so, no processing signal needs to be generated. If not, a correction signal is generated for display.

8. A chiller AI group control virtual-reality interactive display system based on IOE, the system operates according to the chiller AI group control virtual-reality interactive display method based on IOE according to any one of claims 1 to 7, characterized in that: include: The characteristic sequence confirmation end confirms the individual units associated with the chiller, and then confirms the energy consumption characteristic sequence associated with the individual units based on the historical operation data of the individual units; The polygon confirmation end constructs characteristic polygons based on the energy consumption characteristic sequences associated with different units in the chiller, quantizes the values within the energy consumption characteristic sequences, and generates quantized polygons belonging to the chiller based on the quantized values; The optimization parameter execution end confirms the heat characteristics generated by the corresponding operating items of the running equipment, locks the cooling characteristics based on the confirmed heat characteristics, and then confirms and executes the operating parameters of each unit based on the cooling characteristics and quantified polygons.

Images