CN118376029B - Refrigerating system energy saving method adopting AI algorithm - Google Patents
Refrigerating system energy saving method adopting AI algorithm Download PDFInfo
- Publication number
- CN118376029B CN118376029B CN202410806986.5A CN202410806986A CN118376029B CN 118376029 B CN118376029 B CN 118376029B CN 202410806986 A CN202410806986 A CN 202410806986A CN 118376029 B CN118376029 B CN 118376029B
- Authority
- CN
- China
- Prior art keywords
- refrigeration
- load
- temperature
- equipment
- value
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 57
- 238000005057 refrigeration Methods 0.000 claims abstract description 107
- 238000001816 cooling Methods 0.000 claims abstract description 48
- 230000008859 change Effects 0.000 claims abstract description 12
- 238000004458 analytical method Methods 0.000 claims abstract description 11
- 238000010257 thawing Methods 0.000 claims abstract description 6
- 230000008569 process Effects 0.000 claims description 27
- 239000007788 liquid Substances 0.000 claims description 15
- 238000012544 monitoring process Methods 0.000 claims description 15
- 230000001105 regulatory effect Effects 0.000 claims description 13
- 238000012549 training Methods 0.000 claims description 11
- 238000009826 distribution Methods 0.000 claims description 8
- 238000005265 energy consumption Methods 0.000 claims description 8
- 230000003828 downregulation Effects 0.000 claims description 7
- 238000003860 storage Methods 0.000 claims description 7
- 238000005457 optimization Methods 0.000 claims description 4
- 230000001276 controlling effect Effects 0.000 claims description 3
- 230000002787 reinforcement Effects 0.000 abstract 1
- 230000002159 abnormal effect Effects 0.000 description 4
- 238000001704 evaporation Methods 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 230000033228 biological regulation Effects 0.000 description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 230000005611 electricity Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- YCKRFDGAMUMZLT-UHFFFAOYSA-N Fluorine atom Chemical compound [F] YCKRFDGAMUMZLT-UHFFFAOYSA-N 0.000 description 1
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 238000010521 absorption reaction Methods 0.000 description 1
- 238000004378 air conditioning Methods 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000009833 condensation Methods 0.000 description 1
- 230000005494 condensation Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000008020 evaporation Effects 0.000 description 1
- 229910052731 fluorine Inorganic materials 0.000 description 1
- 239000011737 fluorine Substances 0.000 description 1
- 238000007710 freezing Methods 0.000 description 1
- 230000008014 freezing Effects 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000003507 refrigerant Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F25—REFRIGERATION OR COOLING; COMBINED HEATING AND REFRIGERATION SYSTEMS; HEAT PUMP SYSTEMS; MANUFACTURE OR STORAGE OF ICE; LIQUEFACTION SOLIDIFICATION OF GASES
- F25B—REFRIGERATION MACHINES, PLANTS OR SYSTEMS; COMBINED HEATING AND REFRIGERATION SYSTEMS; HEAT PUMP SYSTEMS
- F25B49/00—Arrangement or mounting of control or safety devices
- F25B49/02—Arrangement or mounting of control or safety devices for compression type machines, plants or systems
- F25B49/022—Compressor control arrangements
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F11/00—Control or safety arrangements
- F24F11/88—Electrical aspects, e.g. circuits
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F11/00—Control or safety arrangements
- F24F11/89—Arrangement or mounting of control or safety devices
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F25—REFRIGERATION OR COOLING; COMBINED HEATING AND REFRIGERATION SYSTEMS; HEAT PUMP SYSTEMS; MANUFACTURE OR STORAGE OF ICE; LIQUEFACTION SOLIDIFICATION OF GASES
- F25D—REFRIGERATORS; COLD ROOMS; ICE-BOXES; COOLING OR FREEZING APPARATUS NOT OTHERWISE PROVIDED FOR
- F25D29/00—Arrangement or mounting of control or safety devices
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
Landscapes
- Engineering & Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Combustion & Propulsion (AREA)
- Chemical & Material Sciences (AREA)
- Physics & Mathematics (AREA)
- Thermal Sciences (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Evolutionary Computation (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Medical Informatics (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Devices That Are Associated With Refrigeration Equipment (AREA)
Abstract
The invention discloses a refrigerating system energy-saving method adopting an AI algorithm, which specifically comprises the following steps: s1, acquiring operation parameters of refrigeration equipment and various parameters of a cooling room in a warehouse through gateway equipment, and inputting the parameters into an AI system for parameter analysis; s2, according to the current working condition, adjusting parameters such as load-reducing pressure of the compressor, stop pressure, load-reducing pressure of the evaporative condenser, upper and lower temperature limits of the cold room, load-reducing delay of the compressor, defrosting time interval and the like; the invention relates to the technical field of refrigeration systems of refrigeration houses. According to the refrigerating system energy-saving method adopting the AI reinforcement learning algorithm, the AI system can automatically adjust the setting parameters of the refrigerating system according to the change of the system operation parameters, so that the operation of the air cooler among multiple cooling rooms is matched with the input load of the compressor, the intelligent control can reduce manual intervention, improve the operation energy efficiency ratio of the compressor, and reduce the low-efficiency state of the low-load operation of the refrigerating compressor.
Description
Technical Field
The invention relates to the technical field of refrigeration systems of refrigeration houses, in particular to an energy-saving method of a refrigeration system adopting an AI algorithm.
Background
Refrigeration systems refer to systems that utilize external energy to transfer heat from a cooler substance (or environment) to a warmer substance (or environment), commonly used in refrigeration, freezing, or air conditioning applications. The refrigeration system is generally composed of a compressor, a condenser, an evaporator, an expansion valve and the like, and heat is absorbed and released through circulating working media (such as refrigerant) flowing between the components, so that the cooling effect is achieved. Refrigeration systems come in a variety of different types and operating principles, such as evaporative condensation cycles, absorption refrigeration, heat pumps, and the like. In modern life, refrigeration systems are widely used in the fields of household appliances, commercial equipment, industrial production, and the like.
Chinese patent CN114076492a discloses a controller and a refrigeration system, which comprises a refrigeration device and a controller, wherein the controller can selectively control different refrigeration compartments of the refrigeration device, thereby meeting the requirements of people on the intellectualization and humanization of the refrigerator.
However, the controller only controls the refrigerating system to refrigerate different refrigerating compartments, and when the controller is applied to a storeroom with multiple refrigerating compartments, the refrigerating system simultaneously refrigerates the multiple refrigerating compartments, and because of different numbers of the refrigerating compartments, the load of the refrigerating system is different, and the overload or low-load state of the refrigerating system occurs, the former can cause easy damage to the refrigerating equipment, and the latter can not fully utilize the performance of the refrigerating system, so that the problem of energy waste is caused.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides an energy-saving method of a refrigerating system by adopting an AI algorithm, which solves the problems that the common equipment such as a compressor, evaporation and cooling of the refrigerating system cannot be matched with the terminal warehouse equipment because the goods inlet and outlet quantity of the refrigerating warehouse, the door opening times, the environment temperature and the quantity of the refrigerating rooms are all changed at any time, and the energy consumption in a refrigerating low-load state is high.
In order to achieve the above purpose, the invention is realized by the following technical scheme: an energy-saving method for a refrigerating system adopting an AI algorithm specifically comprises the following steps:
s1, acquiring operation parameters of refrigeration equipment and various parameters of a cooling room in a warehouse through gateway equipment, and inputting the parameters into an AI system for parameter analysis;
S2, according to the current working condition, adjusting parameters such as load-reducing pressure of the compressor, stop pressure, load-reducing pressure of the evaporative condenser, upper and lower temperature limits of the cold space, load-reducing delay of the compressor, defrosting time interval, ammeter difference value and the like;
S3, when the unit load rate is not full, according to the comparison between the temperature of the cold room and the upper limit and the lower limit of the temperature of the cold room, the loading parameters of the compressor are reduced or the upper limit of the temperature is adjusted, the refrigeration of the cold room is increased to enable the compressor to be gradually loaded to be full, or the load-reducing pressure of the compressor is increased or the lower limit of the temperature of the cold room is adjusted, when the refrigeration of the cold room is reduced, the upper limit of the temperature of the cold room is regulated and controlled through an AI system, so that the overall optimization of the refrigeration equipment finds the most economical running state point;
S4, in the process of increasing the cooling capacity or reducing the cooling capacity to perform cooling in S3, monitoring a load value F of the refrigeration equipment, regulating and controlling an initial upper limit value T D of the cooling capacity temperature to a final upper limit value T Z, and operating the refrigeration equipment in full load F M, wherein an intermittent uniform down regulation mode is adopted when the upper limit value is regulated until the refrigeration equipment is full load;
s5, an AI prediction model is established by an AI system, an upper limit value is predicted for a plurality of monitoring refrigerating equipment load value change condition analysis rules, a predicted value and an actual value are recorded for learning and training, and after the AI prediction model meets the requirement, a predicted result is advanced and the upper limit value is directly adjusted downwards in the next operation;
and S6, monitoring the descending speed of the temperature of each cooling room in the cooling process, and adjusting the load distribution proportion of the cooling equipment for cooling each cooling room according to the proportion of the descending speed.
Preferably, the refrigerating equipment is the refrigerating equipment among a compressor, an evaporative condenser, a barrel pump, a liquid receiver and a storehouse cold room in the system, and different cold rooms are put into refrigeration by comparing the temperature with the upper and lower limits of the temperature of the cold rooms; the refrigerating equipment collects data in real time through the PLC and is regulated and controlled by the PLC, the data are transmitted to the switch by the PLC, and the switch is transmitted to the AI system, or the refrigerating equipment is directly connected with the AI system through the PLC.
Preferably, the specific step S2 is as follows:
An upper limit value T U and an initial upper limit value T D are set for the cold room temperature T S, and the refrigerating equipment is started to start refrigerating at the actual cold room temperature T S＞TU.
A lower limit value T T and an initial lower limit value T E are set for the cold room temperature T S, the actual temperature is between the cold room, and the refrigeration equipment stops working at the time of T s＜TE.
Preferably, the specific step of S3 is as follows:
When the unit load rate is not full, according to the comparison between the temperature of the cold room and the upper limit and the lower limit of the temperature of the cold room, the loading parameters of the compressor are reduced or the upper limit of the temperature is adjusted, the refrigeration of the cold room is increased to enable the compressor to be gradually loaded to be full, or the load-reducing pressure of the compressor is increased or the lower limit of the temperature of the cold room is adjusted, when the refrigeration of the cold room is reduced, the upper limit of the temperature of the cold room is regulated and controlled through an AI system, so that the overall optimization of the refrigeration equipment finds the most economical running state point;
preferably, the specific step of S4 is as follows:
And monitoring the running state of the refrigeration equipment in the refrigeration process, recording a real-time load parameter F, setting the load of the full-load state of the refrigeration equipment as F M, gradually reducing the upper limit value according to the rule of reducing the temperature T 0 each time, and reducing the temperature again when the temperature of the refrigeration house reaches the upper limit value each time until F=F M.
Preferably, the specific step of S5 is as follows:
The method comprises the steps of recording a change value establishment subset (F1, F2, F3, & gt, fn) of a load parameter F along with the repeated downward adjustment of an upper limit value in real time, analyzing a change rule of the real-time load parameter F and establishing an AI prediction model, predicting a value of a when Fi=F M, wherein a is a natural number larger than n, namely, the predicted upper limit prediction value is T Y=TL-T0 multiplied by a, recording a predicted result and a final actual T Z value in an AI system for learning and training, correcting the AI prediction model, predicting again and comparing the actual T Z value in the next actual application, and skipping a step-by-step downward adjustment step to directly adjust the upper limit value to the predicted value in the next use when the error value is within an allowable error range T W, namely |T Y-TZ|＜TW.
Preferably, the specific step of S6 is as follows:
In the refrigeration process, monitoring the time t required by the temperature of each cold room in each descending gradient, establishing N subsets (L 1,L2,L3,...,LN) of the cold rooms, wherein the subset of the time t of each L j is (t j 1,tj 2,tj 3,...,tj n), j is any value from 1 to N, and obtaining the average value of the subset t of L j as follows:
tp=(tj 1+tj 2+tj 3+...+tj n)/n；
And (tp 1,tp2,tp3,...,tpN) is an average time subset corresponding to the obtained subset (L 1,L2,L3,...,LN), and the load distribution proportion of the refrigeration equipment for refrigeration among the colds is adjusted according to the proportion of the average time subset.
Preferably, the collected operation parameters of the refrigeration equipment comprise the air suction temperature of the compressor, the air discharge temperature, the loading position, the loading pressure, the load shedding pressure, operation signals of each equipment, electric meter readings, the air discharge pressure of the evaporated cold, the electric meter readings of the evaporated cold, the upper and lower temperature limits, an air cooler in a storehouse, the switching state of a liquid supply valve, the state of a defrosting valve, the degree of superheat, the opening degree of the valve, the current, the temperature, the humidity, the pressure difference of the air cooler, the air outlet speed, the electric meter readings of the air cooler, frosting video and the thickness of a frost layer.
Preferably, when the AI system monitors that the temperature, the pressure and the energy consumption of the refrigeration equipment are abnormally increased, reduced, abnormally fluctuated or out of an expected range, the equipment is abnormally stopped or abnormally operated, the AI system performs early warning to inform workers.
Preferably, each operation parameter of the refrigeration equipment is provided with a threshold value, each parameter is adjusted in the threshold value during normal operation, when refrigeration is performed during adding of a cold room, each parameter of the refrigeration equipment is also adjusted in the threshold value except for the lower limit of the temperature, full load is finally achieved, the adjustment process is recorded in an AI system for learning, and the adjustment process is actively adjusted to the optimal parameter through the AI system after multiple learning mastering rules.
The invention provides an energy-saving method for a refrigerating system by adopting an AI algorithm. Compared with the prior art, the method has the following beneficial effects:
1. According to the refrigerating system energy-saving method adopting the AI algorithm, the AI system can automatically adjust the upper temperature limit of the refrigerating system according to the temperature change in the cold room, so that the operation of the air cooler in the plurality of cold rooms is matched with the input load of the compressor, the intelligent control can reduce manual intervention, improve the operation energy efficiency ratio of the compressor, reduce the low-efficiency state of the low-load operation of the refrigerating compressor, further can perform training and learning, gradually improve the prediction capability, and can more intelligently and directly adjust the upper limit later.
2. According to the energy-saving method of the refrigerating system adopting the AI algorithm, when a new cold room is added, the temperature of each cold room is kept consistent and reduced in a mode of firstly adjusting up and then gradually adjusting down the upper limit of the temperature, and the load state of the refrigerating equipment is monitored in the slow down adjusting process, so that the refrigerating equipment can finally reach a full-load state, and the problems that the refrigerating equipment is damaged and the low load cannot fully exert the performance due to overload are avoided; and the prediction upper limit value can be realized by analyzing the data, the accurate prediction of the upper limit value can be directly realized after the training is carried out for many times, the next down-regulation can be carried out in one step, the problem that the intermittent down-regulation of the refrigeration equipment is likely to stop and restart is avoided, and the efficiency is higher.
3. According to the energy-saving method of the refrigerating system adopting the AI algorithm, through the analysis of the cooling speed of each cold room in the refrigerating process, the actual refrigerating requirement of each cold room can be judged, the actual refrigerating requirement is expressed in a proportional form, the optimal load distribution model is calculated through the analysis of the cooling requirement of a cold storage and the operation data of the refrigerating system, and then the operation parameters of the refrigerating equipment are automatically adjusted according to the scheme so as to ensure that the load is matched with the actual requirement, so that the refrigerating system can be operated in an optimal state, the operation efficiency is improved, and the energy consumption is reduced.
4. According to the refrigerating system energy-saving method adopting the AI algorithm, the AI system can identify abnormal conditions by analyzing the operation data and the state information of the refrigerating equipment, and once the abnormal conditions are found, the AI technology can timely send out early warning information to remind workers to process, so that the influence of faults on the system operation can be avoided, and the maintenance cost and the downtime are reduced.
Drawings
FIG. 1 is a schematic diagram of a system architecture according to the present invention;
FIG. 2 is a flow chart of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, the present invention provides four technical solutions:
First embodiment: an energy-saving method for a refrigerating system adopting an AI algorithm specifically comprises the following steps:
s1, acquiring operation parameters of refrigeration equipment and various parameters of a cooling room in a warehouse through gateway equipment, and inputting the parameters into an AI system for parameter analysis;
S2, according to the current working condition, adjusting parameters such as load-reducing pressure of the compressor, stop pressure, load-reducing pressure of the evaporative condenser, upper and lower temperature limits of the cold space, load-reducing delay of the compressor, defrosting time interval, ammeter difference value and the like;
S3, when the unit load rate is not full, according to the comparison between the temperature of the cold room and the upper limit and the lower limit of the temperature of the cold room, the loading parameters of the compressor are reduced or the upper limit of the temperature is adjusted, the refrigeration of the cold room is increased to enable the compressor to be gradually loaded to be full, or the load-reducing pressure of the compressor is increased or the lower limit of the temperature of the cold room is adjusted, when the refrigeration of the cold room is reduced, the upper limit of the temperature of the cold room is regulated and controlled through an AI system, so that the overall optimization of the refrigeration equipment finds the most economical running state point;
S4, in the process of increasing the cooling capacity or reducing the cooling capacity to perform cooling in S3, monitoring a load value F of the refrigeration equipment, regulating and controlling an initial upper limit value T D of the cooling capacity temperature to a final upper limit value T Z, and operating the refrigeration equipment in full load F M, wherein an intermittent uniform down regulation mode is adopted when the upper limit value is regulated until the refrigeration equipment is full load;
s5, an AI prediction model is established by an AI system, an upper limit value is predicted for a plurality of monitoring refrigerating equipment load value change condition analysis rules, a predicted value and an actual value are recorded for learning and training, and after the AI prediction model meets the requirement, a predicted result is advanced and the upper limit value is directly adjusted downwards in the next operation;
and S6, monitoring the descending speed of the temperature of each cooling room in the cooling process, and adjusting the load distribution proportion of the cooling equipment for cooling each cooling room according to the proportion of the descending speed.
The refrigerating equipment is the refrigerating equipment among a compressor, an evaporative condenser, a barrel pump, a liquid receiver and a storehouse cold room in the system, and different cold rooms are put into refrigeration by comparing the temperature with the upper and lower limits of the temperature of the cold rooms; the refrigerating equipment collects data in real time through the PLC and is regulated and controlled by the PLC, the data are transmitted to the switch by the PLC, and the switch is transmitted to the AI system, or the refrigerating equipment is directly connected with the AI system through the PLC.
The AI system can automatically adjust the upper limit of the temperature of the refrigerating system according to the temperature change in the cooling room, so that the operation of the air cooler between multiple cooling rooms is matched with the input load of the compressor, the intelligent control can reduce manual intervention, improve the operation energy efficiency ratio of the compressor, reduce the low-efficiency state of the low-load operation of the refrigerating compressor, perform training and learning, gradually improve the prediction capability, and further can more intelligently and directly adjust the upper limit.
The second embodiment differs from the first embodiment mainly in that: s2, the specific steps are as follows:
An upper limit value T U and an initial upper limit value T D are set for the cold room temperature T S, the refrigerating equipment is started to start refrigerating at the actual cold room temperature T S＞TU, and the refrigerating equipment stops working at the time of T S＜TD.
The specific steps of S3 are as follows:
when the number N 2 of cold rooms to be refrigerated is increased from the number N 1 of the initial refrigeration, the upper limit value of all cold rooms is firstly adjusted to the highest temperature value T G in the existing temperature of the original N 1 cold rooms, and when the temperature of all cold rooms reaches the temperature value, the upper limit value of the temperature is re-adjusted to the final upper limit value T Z.
The specific steps of S4 are as follows:
And monitoring the running state of the refrigeration equipment in the refrigeration process, recording a real-time load parameter F, setting the load of the full-load state of the refrigeration equipment as F M, gradually reducing the upper limit value according to the rule of reducing the temperature T 0 each time, and reducing the temperature again when the temperature of the refrigeration house reaches the upper limit value each time until F=F M.
The specific steps of S5 are as follows:
The method comprises the steps of recording a change value establishment subset (F1, F2, F3, & gt, fn) of a load parameter F along with the repeated downward adjustment of an upper limit value in real time, analyzing a change rule of the real-time load parameter F and establishing an AI prediction model, predicting a value of a when Fi=F M, wherein a is a natural number larger than n, namely, the predicted upper limit prediction value is T Y=TL-T0 multiplied by a, recording a predicted result and a final actual T Z value in an AI system for learning and training, correcting the AI prediction model, predicting again and comparing an actual T Z value in the next actual application, and skipping a step-down adjustment step to directly lower the upper limit value to the predicted value in the next use when the error value is in an allowable error range T W, namely |T Y-TZ|＜TW (T W is set by manual).
The operation parameters of the refrigeration equipment are all provided with threshold values, the parameters are adjusted in the threshold values during normal operation, when refrigeration is carried out during adding of a cold room, the parameters of the refrigeration equipment are also adjusted in the threshold values except for the lower limit of the temperature, the full load is finally achieved, the adjustment process is recorded in an AI system for learning, and the adjustment process is actively adjusted to the optimal parameters through the AI system after the rules are learned for multiple times.
When a new cold room is added, the temperature of each cold room is kept consistent and reduced by adopting a mode of firstly adjusting the temperature upper limit upwards and then gradually adjusting the temperature lower limit downwards, and the load state of the refrigeration equipment is monitored in the slow down adjustment process, so that the refrigeration equipment can finally reach a full load state, and the problems that the refrigeration equipment is damaged and the low load cannot fully exert the performance due to overload are avoided; the prediction upper limit value can be realized by analyzing the data, the accurate prediction of the upper limit value can be directly realized after the multi-time training is carried out, the problem that the intermittent down-regulation is likely to stop and restart the refrigeration equipment is avoided in one step during the subsequent down-regulation, the efficiency is higher, and the AI system can learn the regulation rule of the self parameters of the refrigeration equipment in the regulation process so as to realize the subsequent active regulation to the optimal parameters and reach the full-load state as soon as possible.
The third embodiment differs from the second embodiment mainly in that: the specific steps of S6 are as follows:
In the refrigeration process, monitoring the time t required by the temperature of each cold room in each descending gradient, establishing N subsets (L 1,L2,L3,...,LN) of the cold rooms, wherein the subset of the time t of each L j is (t j 1,tj 2,tj 3,...,tj n), j is any value from 1 to N, and obtaining the average value of the subset t of L j as follows:
tp=(tj 1+tj 2+tj 3+...+tj n)/n；
And (tp 1,tp2,tp3,...,tpN) is an average time subset corresponding to the obtained subset (L 1,L2,L3,...,LN), and the load distribution proportion of the refrigeration equipment for refrigeration among the colds is adjusted according to the proportion of the average time subset.
The actual refrigeration requirement of each cold room can be judged through the analysis of the cooling speed of each cold room in the refrigeration process, the actual refrigeration requirement of each cold room is expressed in a proportional form, the optimal load distribution model is calculated through the analysis of the cooling requirement of a refrigeration house and the operation data of a refrigeration system, and then the operation parameters of the refrigeration equipment are automatically adjusted according to the scheme so as to ensure that the load is matched with the actual requirement, so that the refrigeration system can be operated in the optimal state, the operation efficiency is improved, and the energy consumption is reduced.
The fourth embodiment differs from the third embodiment mainly in that: the collected operation parameters of the refrigeration equipment comprise the air suction temperature, the air discharge temperature, the loading position, the loading pressure, the unloading pressure, the operation signal, the ammeter reading, the evaporating cold air discharge pressure, the evaporating cold ammeter reading, the upper and lower temperature limits, an air cooler in a storehouse, the switching state of a liquid supply valve and the ammeter reading of the air cooler.
The AI system monitors that the temperature, the pressure and the energy consumption of the refrigeration equipment are abnormally increased, reduced, abnormally fluctuated or out of an expected range, and the equipment is abnormally stopped or abnormally operated, and performs early warning to inform workers.
The AI system can identify abnormal conditions by analyzing the operation data and the state information of the refrigeration equipment, and once the abnormal conditions are found, the AI technology can timely send out early warning information to remind workers to process, so that the influence of faults on the operation of the system can be avoided, and the maintenance cost and the downtime are reduced.
The specific collected integral operation parameters of the refrigeration house comprise:
Static parameters, operation parameters, equipment power, environmental temperature, environmental humidity, suction and exhaust pressure of the compressor, current, load position, suction control pressure (target pressure) of the compressor, suction pressure loading and unloading deviation, compressor loading and unloading delay, compressor restarting interval, compressor frequency converter frequency, shutdown pressure, compressor ammeter, operation signal and operation duration of the whole system;
and (3) evaporating and cooling: the method comprises the steps of ammeter, exhaust pressure, water pump starting pressure of an evaporative condenser, water pump stopping pressure of the evaporative condenser, axial flow fan starting pressure, axial flow fan stopping pressure, water pump starting delay and fan starting delay;
Barrel pump: ammeter, operation signal, pressure, liquid level and expansion valve opening;
condensing evaporator: pressure, liquid level, operating signal, electricity meter;
liquid level, pressure, electricity meter and other parameters of other equipment;
Air cooler, liquid supply valve, hot fluorine valve, return valve, drain valve, air cooler electric current, pressure differential, frost layer thickness, camera frosting condition, storehouse temperature, humidity and storehouse door switch number of times.
The method comprises the steps of collecting field data in real time, calculating energy consumption data at the current moment, combining multiple operation parameters of the system, combining energy consumption data changes, predicting and optimizing the operation parameters, and gradually grasping the operation rules of the operation data of the system.
Different AI models can be established by combining a project barrel pump liquid supply system, a direct expansion liquid supply system form, a single system form, an overlapping system form and the like.
Experimental cases:
Freon direct expansion system for a certain cold storage project in Chongqing, 7000 levels in low-temperature warehouse and 14686 tons in storage tonnage. Gao Wenku 2200, balance and store 4680 tons. The system goes in and out goods steadily, after data access, the model trains, and data comparison is carried out when the training effect is better, and the project switching PLC mode and the AI mode are switched according to the week to run comparison, and the data access cloud platform carries out real-time statistical analysis, and the result is as follows:
the experimental results in the PLC and AI modes are shown in the following table:
energy saving rate: PLC mode power consumption/AI mode power consumption=39565/31875=1.24;
The festival rate: PLC mode power rate/AI mode power rate=27280/22775=1.197;
As indicated above: the power consumption of the refrigeration storage by the original means of the group A is obviously higher than that of the refrigeration storage subjected to the control of the system, after the refrigeration storage is added for a plurality of times, the refrigeration equipment of the original scheme starts to be failed, and the refrigeration equipment controlled by the system operates normally; therefore, under the control of the system, the working efficiency of the refrigeration equipment is obviously improved, the failure rate is reduced, and the overload failure problem cannot occur easily.
And all that is not described in detail in this specification is well known to those skilled in the art.
It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Although embodiments of the present invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made therein without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (6)
1. An energy-saving method for a refrigerating system by adopting an AI algorithm is characterized by comprising the following steps: the method specifically comprises the following steps:
s1, acquiring operation parameters of refrigeration equipment and various parameters of a cooling room in a warehouse through gateway equipment, and inputting the parameters into an AI system for parameter analysis;
S2, according to the current working condition, adjusting the load-reducing pressure of the compressor, the stop pressure, the load-reducing pressure of the evaporative condenser, the upper and lower temperature limits of the cold room, the load-reducing delay of the compressor, the defrosting time interval and the ammeter difference value parameter;
S3, when the unit load rate is not fully loaded, according to the comparison between the temperature of the cold room and the upper limit and the lower limit of the temperature of the cold room, the loading parameters of the compressor are reduced or the upper limit of the temperature is adjusted, the refrigeration of the cold room is increased to enable the compressor to be gradually loaded to be fully loaded, or the load-reducing pressure of the compressor is increased or the lower limit of the temperature of the cold room is adjusted, when the refrigeration of the cold room is reduced, the upper limit of the temperature of the cold room is regulated and controlled through an AI system, so that the overall optimization of the refrigeration equipment finds the most economical running state point, and the method comprises the following specific steps:
When the number N 2 of the cold rooms to be refrigerated is increased on the number N 1 of the initial refrigeration, the upper limit value of the cold rooms is firstly predicted and adjusted to be a proper value of the cold rooms, and the interval 20s can be predicted again to be a proper value according to the current situation according to the cooling conditions of other cold rooms;
S4, in the process of increasing the cooling capacity or reducing the cooling capacity to perform cooling in S3, monitoring a load value F of the cooling equipment, regulating and controlling an initial upper limit value T D of the cooling capacity temperature to a final upper limit value T Z, and operating the cooling equipment in full load F M, wherein an intermittent uniform down regulation mode is adopted when the upper limit value is regulated until the cooling equipment is full load, and the specific steps are as follows:
Monitoring the running state of the refrigeration equipment in the refrigeration process, recording a real-time load parameter F, setting the load of the full-load state of the refrigeration equipment as F M, and adjusting the upper limit value once at intervals of 20s until F=F M;
S5, an AI prediction model is established by an AI system, an upper limit value is predicted for a plurality of monitoring refrigerating equipment load value change condition analysis rules, a predicted value and an actual value are recorded for learning and training, and after the AI prediction model meets the requirement, a predicted result is advanced and the upper limit value is directly adjusted downwards in the next operation, wherein the method comprises the following specific steps:
The method comprises the steps of recording a change value establishment subset (F1, F2, F3, & gt, fn) of a load parameter F along with the repeated downward adjustment of an upper limit value in real time, analyzing a change rule of the real-time load parameter F and establishing an AI prediction model, predicting a value of a when Fi=F M, wherein a is a natural number larger than n, namely, the predicted upper limit prediction value is T Y=TL-T0 multiplied by a, recording a predicted result and a final actual T Z value in an AI system for learning and training, correcting the AI prediction model, predicting again and comparing an actual T Z value in the next actual application, and skipping a gradual downward adjustment step to directly adjust the upper limit value to the predicted value in the next use when the error value is within an allowable error range T W, namely |T Y-TZ|＜TW;
s6, monitoring the descending speed of the temperature of each cooling room in the cooling process, and adjusting the load distribution proportion of the cooling equipment for cooling each cooling room according to the proportion of the descending speed, wherein the specific steps are as follows:
In the refrigeration process, monitoring the time t required by the temperature of each cold room in each descending gradient, establishing N subsets (L 1,L2,L3,...,LN) of the cold rooms, wherein the subset of the time t of each L j is (t j 1,tj 2,tj 3,...,tj n), j is any value from 1 to N, and obtaining the average value of the subset t of L j as follows:
tp=(tj 1+tj 2+tj 3+...+tj n)/n；
And (tp 1,tp2,tp3,...,tpN) is an average time subset corresponding to the obtained subset (L 1,L2,L3,...,LN), and the load distribution proportion of the refrigeration equipment for refrigeration among the colds is adjusted according to the proportion of the average time subset.
2. The method for saving energy in a refrigeration system using AI algorithm of claim 1, wherein: the refrigerating equipment is the refrigerating equipment among a compressor, an evaporative condenser, a barrel pump, a liquid receiver and a storehouse cold room in the system, and different cold rooms are put into refrigeration by comparing the temperature with the upper and lower limits of the temperature of the cold rooms; the refrigerating equipment collects data in real time through the PLC and is regulated and controlled by the PLC, the data are transmitted to the switch by the PLC, and the switch is transmitted to the AI system, or the refrigerating equipment is directly connected with the AI system through the PLC.
3. The method for saving energy in a refrigeration system using AI algorithm of claim 1, wherein: the specific step of S2 is as follows:
Setting an upper limit value T U and an initial upper limit value T D for the cold room temperature T S, and starting the refrigeration equipment to start refrigeration when the cold room actual temperature T S＞TU;
A lower limit value T T and an initial lower limit value T E are set for the cold room temperature T S, the actual temperature is between the cold room, and the refrigeration equipment stops working at the time of T s＜TE.
4. The method for saving energy in a refrigeration system using AI algorithm of claim 1, wherein: the collected operation parameters of the refrigeration equipment comprise compressor suction temperature, exhaust temperature, loading load position, loading pressure, load shedding pressure, operation signals, meter readings of each equipment, exhaust pressure of evaporated cooling, meter readings of evaporated cooling, operation signals of evaporated cooling, upper and lower temperature limits, an air cooler in a storehouse, on-off states of liquid supply valves, operation signals of the air cooler, meter readings, liquid supply valve opening signals, defrosting valve signals, storehouse humidity, air outlet speed, air outlet wind speed, valve opening, superheat degree, pressure, temperature, liquid level, equipment power, air inlet and outlet pressure difference of fans, current, air outlet wind speed and the like of each liquid storage.
5. The method for saving energy in a refrigeration system using AI algorithm of claim 4, wherein: the AI system monitors that the temperature, the pressure and the energy consumption of the refrigeration equipment are abnormally increased, reduced, abnormally fluctuated or out of an expected range, and the equipment is abnormally stopped or abnormally operated, and performs early warning to inform workers.
6. The method for saving energy in a refrigeration system using AI algorithm of claim 4, wherein: the operation parameters of the refrigeration equipment are all provided with threshold values, the parameters are adjusted in the threshold values during normal operation, when refrigeration is carried out during adding of a cold room, the parameters of the refrigeration equipment are also adjusted in the threshold values except for the lower limit of the temperature, the full load is finally achieved, the adjustment process is recorded in an AI system for learning, and the adjustment process is actively adjusted to the optimal parameters through the AI system after the rules are learned for multiple times.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410806986.5A CN118376029B (en) | 2024-06-21 | 2024-06-21 | Refrigerating system energy saving method adopting AI algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410806986.5A CN118376029B (en) | 2024-06-21 | 2024-06-21 | Refrigerating system energy saving method adopting AI algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118376029A CN118376029A (en) | 2024-07-23 |
| CN118376029B true CN118376029B (en) | 2024-08-23 |
Family
ID=91906062
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410806986.5A Active CN118376029B (en) | 2024-06-21 | 2024-06-21 | Refrigerating system energy saving method adopting AI algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118376029B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102193567A (en) * | 2010-03-10 | 2011-09-21 | 同方人工环境有限公司 | Method for controlling stepless adjustment of water-source screw unit |
| CN108592515A (en) * | 2018-06-04 | 2018-09-28 | 北京中冷高科制冷设备有限公司 | A kind of control method of cold storage refrigerating system |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP3360362B2 (en) * | 1993-07-26 | 2002-12-24 | ダイキン工業株式会社 | Refrigeration equipment |
| WO2020107851A1 (en) * | 2018-11-29 | 2020-06-04 | 天津大学 | Low-cost commissioning method and system for air conditioning system based on existing large-scale public building |
| CN114963414B (en) * | 2022-06-08 | 2023-11-24 | 山东润一智能科技有限公司 | Intelligent air conditioning system regulating and controlling device based on AI data analysis |
-
2024
- 2024-06-21 CN CN202410806986.5A patent/CN118376029B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102193567A (en) * | 2010-03-10 | 2011-09-21 | 同方人工环境有限公司 | Method for controlling stepless adjustment of water-source screw unit |
| CN108592515A (en) * | 2018-06-04 | 2018-09-28 | 北京中冷高科制冷设备有限公司 | A kind of control method of cold storage refrigerating system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118376029A (en) | 2024-07-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112283993B (en) | Refrigeration control method and device and refrigeration equipment | |
| JP2005114295A (en) | Heat source system and controller | |
| CN108534394B (en) | Group control optimization control method for loading and unloading of double units of ground source heat pump | |
| CN113790542B (en) | Multi-module water chilling unit and scheduling control method thereof | |
| CN116255716A (en) | Central air conditioner artificial intelligent load prediction energy-saving strategy | |
| CN114459133A (en) | Energy-saving control method and energy-saving control system for central air-conditioning system | |
| CN117387250A (en) | Multi-module air source heat pump system and grouping control method thereof | |
| CN108168170A (en) | A kind of cold storage refrigerating system intelligent control method based on on-line identification | |
| CN112665239A (en) | Water chilling unit starting method and device and water chilling unit | |
| CN118376029B (en) | Refrigerating system energy saving method adopting AI algorithm | |
| CN114087825A (en) | A kind of refrigerator energy saving control method | |
| CN117781493A (en) | Fluorine pump pressure refrigeration system and control method and control system thereof | |
| CN111023693A (en) | High-precision temperature control method, storage medium and control device | |
| CN115218346B (en) | Heat accumulation defrosting control method and air conditioning unit | |
| CN114322220B (en) | Air conditioning device and control method thereof | |
| CN115309056A (en) | Control method of multiple water chilling units | |
| CN115540374A (en) | Refrigerating unit | |
| CN114608258A (en) | Defrosting control method of refrigerator refrigerating system based on electronic expansion valve | |
| CN211400500U (en) | High-precision temperature control device | |
| CN105899899A (en) | Refrigerator with improved energy management mode and method for controlling the refrigerator | |
| CN114413428A (en) | Central air conditioner | |
| CN114396709A (en) | Multi-module air conditioning system, control method thereof and storage medium | |
| CN118049768B (en) | Liquid cooling system control method and device and liquid cooling system | |
| CN111578549B (en) | Condensing unit capable of adjusting cooling capacity and control method thereof | |
| CN220287880U (en) | Energy-saving control system of refrigeration house evaporation system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |