Disclosure of Invention
The invention overcomes the defects of the prior art and provides an intelligent control method and system for a cooling system based on performance degradation evaluation of a fluorinated liquid.
In order to achieve the above purpose, the invention adopts the following technical scheme:
the invention provides an intelligent control method of a cooling system based on performance degradation evaluation of a fluorinated liquid, which comprises the following steps:
acquiring cooling performance index data information of the fluorinated solution in each cooling system, and performing performance membership evaluation on the cooling performance index data information of the fluorinated solution in the cooling system through a decision tree model to acquire the cooling performance evaluation membership of the fluorinated solution;
constructing a fluoride liquid performance degradation prediction model based on the cooling performance evaluation membership degree of the fluoride liquid, the deep neural network and the Markov chain, and predicting the cooling performance evaluation membership degree of the fluoride liquid in each cooling system of the current time stamp through the fluoride liquid performance degradation prediction model;
constructing a cooling system state identification model based on a convolutional neural network and a twin network, and tracking and identifying the cooling system with each cooling performance evaluation membership degree through the cooling system state identification model to acquire the cooling performance characteristic data distribution condition of the cooling system in a target area;
And acquiring cooling demand data information in the current target area, and generating a related cooling control scheme according to the cooling demand data information in the current target area and the cooling performance characteristic data distribution condition of the cooling system in the target area.
Further, in the method, performance membership evaluation is performed on cooling performance index data information of the fluorinated solution in the cooling system through the decision tree model, and the cooling performance evaluation membership of the fluorinated solution is obtained, which specifically comprises the following steps:
setting a plurality of threshold ranges of cooling performance evaluation membership degrees, introducing a decision tree model, setting a splitting standard according to the threshold ranges of the cooling performance evaluation membership degrees, and constructing a sample data set based on cooling performance index data information of the fluoridized liquid in the cooling system;
constructing a root node according to a sample data set, initializing and splitting the root node based on splitting criteria to generate a plurality of new splitting nodes, and judging whether all sample data in the new splitting nodes at least contain sample data in a threshold range of other cooling performance evaluation membership degrees;
when all sample data in the new split node at least contain one sample data in the threshold range of other cooling performance evaluation membership degrees, continuously splitting the new split node;
Outputting the new split node and generating leaf nodes when all sample data in the new split node do not contain sample data in the threshold range of other cooling performance evaluation membership degrees, acquiring the cooling performance evaluation membership degree of each leaf node, and outputting the cooling performance evaluation membership degree as the cooling performance evaluation membership degree of the fluoridation liquid.
Further, in the method, a fluoride fluid degradation prediction model is constructed based on the cooling performance evaluation membership degree of the fluoride fluid, the deep neural network and the Markov chain, and specifically comprises the following steps:
constructing a time stamp, fusing the time stamp and the cooling performance evaluation membership degree of the fluorinated liquid to construct a sample data set of the cooling performance evaluation membership degree of the fluorinated liquid based on a time sequence, and constructing a fluorinated liquid degradation prediction model based on a deep neural network;
introducing a Markov chain, calculating a transition probability value of the cooling performance evaluation membership degree of the fluorinated liquid in each timestamp in the sample data set to the cooling performance evaluation membership degree of the next level through the Markov chain, and constructing a transition probability matrix;
inputting the transition probability matrix into a fluorinated solution performance degradation prediction model for coding learning, fusing a circulating space attention mechanism, focusing attention on transition probability features in the transition probability matrix through the circulating space attention mechanism, and generating an attention feature map;
And (3) carrying out cooperative work on the attention feature map and the hidden layer, updating the state of the hidden layer, and after the fluoride liquid performance degradation prediction model meets the preset requirement, storing model parameters and outputting the fluoride liquid performance degradation prediction model.
Further, in the method, the cooling performance evaluation membership degree of the fluorinated liquid in each cooling system of the current time stamp is predicted by using a fluorinated liquid degradation prediction model, and specifically includes:
presetting a transition probability threshold, acquiring cooling performance evaluation membership of the fluorinated liquid in each cooling system in the previous time stamp, and inputting the cooling performance evaluation membership of the fluorinated liquid in each cooling system into a fluorinated liquid degradation prediction model for prediction;
obtaining a transition probability value of the cooling performance evaluation membership degree of the fluorinated liquid in each cooling system in the previous time stamp to the cooling performance evaluation membership degree of the next level through prediction, and judging whether the transition probability value is larger than a transition probability threshold value;
when the transition probability value is larger than the transition probability threshold value, taking the next grade of cooling performance evaluation membership degree of the fluorinated liquid in the cooling system in the previous time stamp as the cooling performance evaluation membership degree of the fluorinated liquid in the cooling system in the current time stamp;
And when the transition probability value is not greater than the transition probability threshold value, taking the cooling performance evaluation membership degree of the fluorinated liquid in the cooling system in the previous time stamp as the cooling performance evaluation membership degree of the fluorinated liquid in the cooling system in the current time stamp.
Further, in the method, a cooling system state identification model is constructed based on a convolutional neural network and a twin network, and tracking identification is performed on the cooling system with each cooling performance evaluation membership degree through the cooling system state identification model, so as to obtain the cooling performance characteristic data distribution condition of the cooling system in the target area, and the method specifically comprises the following steps:
constructing a cooling system state identification model based on a convolutional neural network, fusing a twin network, acquiring a plurality of cooling systems with cooling performance evaluation membership, and constructing a sample training data set according to the cooling systems with the cooling performance evaluation membership;
the method comprises the steps of arranging and combining sample training data sets, initializing training sample pairs according to the sample training data sets, calculating the similarity between training samples in the training sample pairs through a twin network, and taking sample pairs with the similarity greater than a preset similarity as similar sample pairs;
taking a sample pair with the similarity not greater than the preset similarity as a heterogeneous sample pair, expanding a sample training data set according to the similar sample pair and the heterogeneous sample pair to generate a new sample training set, and inputting the new sample training set into a cooling system state identification model to carry out coding learning;
After the loss function converges to a preset value, model parameters of a cooling system state identification model are saved, the cooling system state identification model is output, and the cooling system with each cooling performance evaluation membership degree is tracked and identified through the cooling system state identification model, so that the cooling performance characteristic data distribution condition of the cooling system in the target area is obtained.
Further, in the method, cooling demand data information in the current target area is obtained, and a related cooling control scheme is generated according to the cooling demand data information in the current target area and the cooling performance characteristic data distribution condition of the cooling system in the target area, and specifically includes:
acquiring cooling demand data information in a current target area, and acquiring a minimum threshold value and a maximum threshold value of cooling performance characteristics of a cooling system in the target area according to the cooling performance characteristic data distribution condition of the cooling system in the target area;
constructing a cooling performance characteristic threshold range of the cooling system in the target area based on the minimum cooling performance characteristic threshold and the maximum cooling performance characteristic threshold of the cooling system in the target area, and judging whether the cooling demand data information in the current target area is within the cooling performance characteristic threshold range of the cooling system in the target area;
When the cooling demand data information in the current target area is within the cooling performance characteristic threshold range of the cooling system in the target area, constructing a retrieval tag according to the cooling demand data information in the current target area;
searching according to the search tag, and calculating the adaptation degree between the cooling demand data information in the current target area and each cooling system in the cooling performance characteristic data distribution condition of the cooling system in the target area;
when the adaptation degree is greater than the preset adaptation degree, generating a related cooling control scheme according to the cooling system corresponding to the adaptation degree which is greater than the preset adaptation degree, and outputting the related cooling control scheme.
The second aspect of the invention provides an intelligent control system of a cooling system based on performance degradation evaluation of a fluorinated liquid, the system comprises a memory and a processor, the memory comprises an intelligent control method program of the cooling system based on the performance degradation evaluation of the fluorinated liquid, and when the intelligent control method program of the cooling system based on the performance degradation evaluation of the fluorinated liquid is executed by the processor, the following steps are realized:
acquiring cooling performance index data information of the fluorinated solution in each cooling system, and performing performance membership evaluation on the cooling performance index data information of the fluorinated solution in the cooling system through a decision tree model to acquire the cooling performance evaluation membership of the fluorinated solution;
Constructing a fluoride liquid performance degradation prediction model based on the cooling performance evaluation membership degree of the fluoride liquid, the deep neural network and the Markov chain, and predicting the cooling performance evaluation membership degree of the fluoride liquid in each cooling system of the current time stamp through the fluoride liquid performance degradation prediction model;
constructing a cooling system state identification model based on a convolutional neural network and a twin network, and tracking and identifying the cooling system with each cooling performance evaluation membership degree through the cooling system state identification model to acquire the cooling performance characteristic data distribution condition of the cooling system in a target area;
and acquiring cooling demand data information in the current target area, and generating a related cooling control scheme according to the cooling demand data information in the current target area and the cooling performance characteristic data distribution condition of the cooling system in the target area.
A third aspect of the present invention provides a computer-readable storage medium including therein a cooling system intelligent control method program based on a fluorinated liquid performance degradation evaluation, which when executed by a processor, implements the steps of any one of the cooling system intelligent control methods based on a fluorinated liquid performance degradation evaluation.
The invention solves the defects existing in the background technology, and has the following beneficial effects:
according to the invention, the cooling performance index data information of the fluorinated liquid in each cooling system is obtained, the performance membership degree evaluation is carried out on the cooling performance index data information of the fluorinated liquid in the cooling system through a decision tree model, the cooling performance evaluation membership degree of the fluorinated liquid is obtained, a fluorinated liquid performance degradation prediction model is built based on the cooling performance evaluation membership degree of the fluorinated liquid, a deep neural network and a Markov chain, the cooling performance evaluation membership degree of the fluorinated liquid in each cooling system is predicted through the fluorinated liquid performance degradation prediction model, a cooling system state recognition model is built based on the convolutional neural network and a twin network, tracking recognition is carried out on the cooling system with each cooling performance evaluation membership degree through the cooling system state recognition model, the cooling performance characteristic data distribution condition of the cooling system in a target area is obtained, and finally, a related cooling control scheme is generated according to the cooling requirement data information in the current target area and the cooling performance characteristic data distribution condition of the cooling system in the target area. According to the invention, the cooling performance degradation condition of the fluorinated liquid is evaluated by fusing the deep neural network and the Markov chain, so that the evaluation accuracy of the cooling performance degradation condition of the fluorinated liquid can be improved, and on the other hand, the twin network and the convolution neural network are fused, so that the tracking accuracy of the cooling performance of the cooling system can be improved, the cooling distribution is performed according to the cooling demand data information in the current target area and the actual performance condition of the cooling system, the cooling effect of equipment is ensured, and the normal performance of corresponding working equipment is maintained.
Detailed Description
In order that the above-recited objects, features and advantages of the present invention will be more clearly understood, a more particular description of the invention will be rendered by reference to the appended drawings and appended detailed description. It should be noted that, in the case of no conflict, the embodiments of the present application and the features in the embodiments may be combined with each other.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, however, the present invention may be practiced in other ways than those described herein, and therefore the scope of the present invention is not limited to the specific embodiments disclosed below.
As shown in fig. 1, the first aspect of the present invention provides a cooling system intelligent control method based on performance degradation evaluation of a fluorinated liquid, which comprises the following steps:
s102, acquiring cooling performance index data information of the fluorinated liquid in each cooling system, and performing performance membership evaluation on the cooling performance index data information of the fluorinated liquid in the cooling system through a decision tree model to acquire the cooling performance evaluation membership of the fluorinated liquid;
s104, constructing a fluoride fluid degradation prediction model based on the cooling performance evaluation membership degree of the fluoride fluid, the deep neural network and the Markov chain, and predicting the cooling performance evaluation membership degree of the fluoride fluid in each cooling system of the current time stamp through the fluoride fluid degradation prediction model;
s106, constructing a cooling system state identification model based on the convolutional neural network and the twin network, and tracking and identifying the cooling system with each cooling performance evaluation membership degree through the cooling system state identification model to acquire the cooling performance characteristic data distribution condition of the cooling system in the target area;
S108, acquiring cooling demand data information in the current target area, and generating a related cooling control scheme according to the cooling demand data information in the current target area and the cooling performance characteristic data distribution condition of the cooling system in the target area.
It should be noted that, the invention evaluates the degradation condition of the cooling performance of the fluorinated solution by fusing the deep neural network and the markov chain, so as to improve the evaluation accuracy of the degradation condition of the cooling performance of the fluorinated solution, and on the other hand, the invention fuses the twin network and the convolution neural network, so as to improve the tracking accuracy of the cooling performance of the cooling system, thereby performing cooling distribution according to the cooling demand data information in the current target area and the actual performance condition of the cooling system, ensuring the cooling effect of the equipment, and maintaining the normal performance of the corresponding working equipment. The cooling performance index data information may be data such as how much heat the fluorinated liquid absorbs and how much the temperature rises within a unit time.
As shown in fig. 2, in the method, performance membership evaluation is further performed on cooling performance index data information of the fluorinated solution in the cooling system through a decision tree model, so as to obtain the cooling performance evaluation membership of the fluorinated solution, which specifically includes:
S202, setting a plurality of threshold ranges of cooling performance evaluation membership degrees, introducing a decision tree model, setting splitting standards according to the threshold ranges of the cooling performance evaluation membership degrees, and constructing a sample data set based on cooling performance index data information of the fluoridized liquid in a cooling system;
s204, constructing a root node according to a sample data set, carrying out initialization splitting on the root node based on splitting criteria, generating a plurality of new splitting nodes, and judging whether all sample data in the new splitting nodes at least contain sample data in a threshold range of other cooling performance evaluation membership degrees;
s206, when all sample data in the new split node at least contain sample data in a threshold range of other cooling performance evaluation membership degrees, performing continuous split on the new split node;
and S208, outputting the new split node and generating leaf nodes when all sample data in the new split node do not contain sample data in the threshold range of other cooling performance evaluation membership degrees, acquiring the cooling performance evaluation membership degree of each leaf node, and outputting the cooling performance evaluation membership degree as the cooling performance evaluation membership degree of the fluorinated liquid.
It should be noted that the cooling performance evaluation membership degree includes membership degrees such as super-strong cooling performance, high cooling performance, medium-high cooling performance, poor cooling performance, etc., where a threshold range of the cooling performance evaluation membership degree is that the cooling performance is poor, for example, 0-1000J/min of heat absorbed by the fluorinated solution in unit time, and related technicians can set according to actual conditions.
Further, in the method, a fluoride fluid degradation prediction model is constructed based on the cooling performance evaluation membership degree of the fluoride fluid, the deep neural network and the Markov chain, and specifically comprises the following steps:
constructing a time stamp, fusing the time stamp and the cooling performance evaluation membership degree of the fluorinated liquid to construct a sample data set of the cooling performance evaluation membership degree of the fluorinated liquid based on a time sequence, and constructing a fluorinated liquid degradation prediction model based on a deep neural network;
introducing a Markov chain, calculating a transition probability value of the cooling performance evaluation membership degree of the fluorinated liquid in each timestamp in the sample data set to the cooling performance evaluation membership degree of the next level through the Markov chain, and constructing a transition probability matrix;
inputting the transition probability matrix into a fluorinated solution performance degradation prediction model for coding learning, fusing a circulating space attention mechanism, focusing attention on transition probability features in the transition probability matrix through the circulating space attention mechanism, and generating an attention feature map;
and (3) carrying out cooperative work on the attention feature map and the hidden layer, updating the state of the hidden layer, and after the fluoride liquid performance degradation prediction model meets the preset requirement, storing model parameters and outputting the fluoride liquid performance degradation prediction model.
In addition, in a long time sequence, the cooling performance evaluation membership degree of the fluorinated liquid always transits from one membership degree state to another membership degree state, for example, the cooling performance is transited to the cooling performance from high, and a transition probability value can be calculated through a Markov chain, so that the prediction accuracy of predicting the membership degree state value of the current timestamp is improved.
Further, in the method, the cooling performance evaluation membership degree of the fluorinated liquid in each cooling system of the current time stamp is predicted by using a fluorinated liquid degradation prediction model, and specifically includes:
presetting a transition probability threshold, acquiring cooling performance evaluation membership of the fluorinated liquid in each cooling system in the previous time stamp, and inputting the cooling performance evaluation membership of the fluorinated liquid in each cooling system into a fluorinated liquid degradation prediction model for prediction;
obtaining a transition probability value of the cooling performance evaluation membership degree of the fluorinated liquid in each cooling system in the previous time stamp to the cooling performance evaluation membership degree of the next level through prediction, and judging whether the transition probability value is larger than a transition probability threshold value;
when the transition probability value is larger than the transition probability threshold value, taking the next grade of cooling performance evaluation membership degree of the fluorinated liquid in the cooling system in the previous time stamp as the cooling performance evaluation membership degree of the fluorinated liquid in the cooling system in the current time stamp;
And when the transition probability value is not greater than the transition probability threshold value, taking the cooling performance evaluation membership degree of the fluorinated liquid in the cooling system in the previous time stamp as the cooling performance evaluation membership degree of the fluorinated liquid in the cooling system in the current time stamp.
Note that when the transition probability value is larger than the transition probability threshold value, the transition from one state to another state is described.
As shown in fig. 3, in the method, a cooling system state identification model is further constructed based on a convolutional neural network and a twin network, and tracking identification is performed on the cooling system with each cooling performance evaluation membership degree through the cooling system state identification model, so as to obtain the cooling performance characteristic data distribution condition of the cooling system in the target area, which specifically includes:
s302, constructing a cooling system state identification model based on a convolutional neural network, fusing a twin network, acquiring a plurality of cooling systems with cooling performance evaluation membership, and constructing a sample training data set according to the cooling systems with the cooling performance evaluation membership;
s304, initializing a training sample pair according to a sample training data set by arranging and combining the sample training data set, calculating the similarity between training samples in the training sample pair through a twin network, and taking a sample pair with the similarity greater than a preset similarity as a similar sample pair;
S306, taking a sample pair with similarity not greater than preset similarity as a heterogeneous sample pair, expanding a sample training data set according to the homogeneous sample pair and the heterogeneous sample pair to generate a new sample training set, and inputting the new sample training set into a cooling system state recognition model to perform coding learning;
and S308, after the loss function is converged to a preset value, saving model parameters of the cooling system state identification model, outputting the cooling system state identification model, and tracking and identifying the cooling system with each cooling performance evaluation membership degree through the cooling system state identification model to acquire the cooling performance characteristic data distribution condition of the cooling system in the target area.
It should be noted that, since the input through the twin network is a sample pair, the new sample training set is generated by expanding the sample training data set according to the similar sample pair and the heterogeneous sample pair, so that the data amount can be greatly increased by the pairing expansion method, and the total amount is equal to the sum of the similar and heterogeneous sample pairs. Compared with the problem of small sample fault identification, the method reduces the difficulty in the modeling and identification process, thereby improving the tracking precision of the cooling system state identification model, further improving the tracking precision of the cooling performance characteristic data of each cooling system in the target area, and ensuring higher monitoring precision of the cooling system.
Further, in the method, cooling demand data information in the current target area is obtained, and a related cooling control scheme is generated according to the cooling demand data information in the current target area and the cooling performance characteristic data distribution condition of the cooling system in the target area, and specifically includes:
acquiring cooling demand data information in a current target area, and acquiring a minimum threshold value and a maximum threshold value of cooling performance characteristics of a cooling system in the target area according to the cooling performance characteristic data distribution condition of the cooling system in the target area;
constructing a cooling performance characteristic threshold range of the cooling system in the target area based on the minimum cooling performance characteristic threshold and the maximum cooling performance characteristic threshold of the cooling system in the target area, and judging whether the cooling demand data information in the current target area is within the cooling performance characteristic threshold range of the cooling system in the target area;
when the cooling demand data information in the current target area is within the cooling performance characteristic threshold range of the cooling system in the target area, constructing a retrieval tag according to the cooling demand data information in the current target area;
searching according to the search tag, and calculating the adaptation degree between the cooling demand data information in the current target area and each cooling system in the cooling performance characteristic data distribution condition of the cooling system in the target area;
When the adaptation degree is greater than the preset adaptation degree, generating a related cooling control scheme according to the cooling system corresponding to the adaptation degree which is greater than the preset adaptation degree, and outputting the related cooling control scheme.
It should be noted that, in an equipment working area, one or more cooling equipment supplies corresponding equipment to cool, due to the influence of cooling performance, the cooling system does not necessarily conform to cooling requirement data information (such as heat and temperature required to be reduced within a unit time value) in the current target area, when the cooling requirement data information in the current target area is within a cooling performance characteristic threshold range of the cooling system in the target area, it is described whether the corresponding equipment exists or can cool, because performance membership degrees, cooling characteristics and the like of all the cooling equipment in the target area are recorded in the cooling performance characteristic data distribution situation, when the adaptation degree is greater than the preset adaptation degree, a related cooling control scheme is generated according to the cooling system corresponding to the adaptation degree greater than the preset adaptation degree, and the corresponding equipment temperature can be maintained within the preset temperature, thereby improving cooling rationality of the cooling system in the target area.
In addition, the method can further comprise the following steps:
when the cooling demand data information in the current target area is not within the cooling performance characteristic threshold range of the cooling system in the target area, constructing a second retrieval tag according to the cooling demand data information in the current target area;
searching through big data based on the second search tag, obtaining a plurality of candidate fluorinated liquid cooling systems, obtaining historical service life duration information of the candidate fluorinated liquid cooling systems, and constructing a long-life sorting table in historical use;
inputting the historical service life time information of the candidate fluorinated liquid cooling system into the long-life sequencing table for sequencing when in historical use, and obtaining the candidate fluorinated liquid cooling system with the historical service life longer than the preset historical service life time;
generating related recommendation information according to the candidate fluorinated liquid cooling system with the historical service life longer than the preset historical service life, and displaying the related recommendation information in a preset mode.
It should be noted that, when the cooling requirement data information in the current target area is not within the cooling performance characteristic threshold range of the cooling system in the target area, it is indicated that the fluoride liquid cooling system in the target area is insufficient to achieve heat dissipation, and due to the fact that the equipment may be updated or due to the fact that the heat dissipation requirement of related equipment in the target area is higher, by the method, when the cooling requirement data information in the current target area is not within the cooling performance characteristic threshold range of the cooling system in the target area, a proper cooling equipment can be recommended to cool.
In addition, the method can further comprise the following steps:
acquiring demand information of related equipment in a target area, initializing quantity information of cooling systems in the target area, acquiring cooling performance characteristic data information of each cooling system, and calculating total cooling performance characteristic data information according to the cooling performance characteristic data information of the cooling systems and the quantity information of the cooling systems in the target area;
introducing a genetic algorithm, setting a genetic algebra according to the heritage algorithm, judging whether the total cooling performance characteristic data information is smaller than the requirement information of related equipment in the target area, outputting the quantity information of cooling systems in the target area if the total cooling performance characteristic data information is not smaller than the requirement information of the related equipment in the target area, and constructing the cooling system Internet of things according to the quantity information of the cooling systems in the target area;
when the total cooling performance characteristic data information is smaller than the requirement information of related equipment in the target area, inheriting the quantity information of the cooling systems in the target area according to the inheritance algebra, and adjusting the quantity information of the cooling systems in the target area;
outputting the quantity information of the cooling systems in the target area until the total cooling performance characteristic data information is not smaller than the requirement information of the related equipment in the target area, and constructing the cooling system Internet of things according to the quantity information of the cooling systems in the target area.
It should be noted that, because the demand information of the related devices in the target area may change, for example, the related devices needing to be cooled in the target area change, and because the cooling performance characteristic data information of the cooling system changes, the total cooling performance characteristic data information of the cooling system in the target area changes, which is insufficient for supporting the cooling of the devices, the method can periodically adjust the quantity information of the cooling system in the target area according to the actual situation, so as to construct a more reasonable cooling system internet of things.
As shown in fig. 4, the second aspect of the present invention provides an intelligent control system 4 for a cooling system based on evaluation of performance degradation of a fluorinated liquid, the system 4 comprising a memory 41 and a processor 42, the memory 41 comprising a program for an intelligent control method for a cooling system based on evaluation of performance degradation of a fluorinated liquid, the program for an intelligent control method for a cooling system based on evaluation of performance degradation of a fluorinated liquid, when executed by the processor 42, implementing the steps of:
acquiring cooling performance index data information of the fluorinated solution in each cooling system, and performing performance membership evaluation on the cooling performance index data information of the fluorinated solution in the cooling system through a decision tree model to acquire the cooling performance evaluation membership of the fluorinated solution;
Constructing a fluoride liquid performance degradation prediction model based on the cooling performance evaluation membership degree of the fluoride liquid, the deep neural network and the Markov chain, and predicting the cooling performance evaluation membership degree of the fluoride liquid in each cooling system of the current time stamp through the fluoride liquid performance degradation prediction model;
constructing a cooling system state identification model based on a convolutional neural network and a twin network, and tracking and identifying the cooling system with each cooling performance evaluation membership degree through the cooling system state identification model to acquire the cooling performance characteristic data distribution condition of the cooling system in a target area;
and acquiring cooling demand data information in the current target area, and generating a related cooling control scheme according to the cooling demand data information in the current target area and the cooling performance characteristic data distribution condition of the cooling system in the target area.
A third aspect of the present invention provides a computer-readable storage medium including therein a cooling system intelligent control method program based on a fluorinated liquid performance degradation evaluation, which when executed by a processor, implements the steps of any one of the cooling system intelligent control methods based on a fluorinated liquid performance degradation evaluation.
In the several embodiments provided in this application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above described device embodiments are only illustrative, e.g. the division of the units is only one logical function division, and there may be other divisions in practice, such as: multiple units or components may be combined or may be integrated into another system, or some features may be omitted, or not performed. In addition, the various components shown or discussed may be coupled or directly coupled or communicatively coupled to each other via some interface, whether indirectly coupled or communicatively coupled to devices or units, whether electrically, mechanically, or otherwise.
The units described above as separate components may or may not be physically separate, and components shown as units may or may not be physical units; can be located in one place or distributed to a plurality of network units; some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in each embodiment of the present invention may be integrated in one processing unit, or each unit may be separately used as one unit, or two or more units may be integrated in one unit; the integrated units may be implemented in hardware or in hardware plus software functional units.
Those of ordinary skill in the art will appreciate that: all or part of the steps for implementing the above method embodiments may be implemented by hardware related to program instructions, and the foregoing program may be stored in a computer readable storage medium, where the program, when executed, performs steps including the above method embodiments; and the aforementioned storage medium includes: a mobile storage device, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk or an optical disk, or the like, which can store program codes.
Alternatively, the above-described integrated units of the present invention may be stored in a computer-readable storage medium if implemented in the form of software functional modules and sold or used as separate products. Based on such understanding, the technical solutions of the embodiments of the present invention may be embodied in essence or a part contributing to the prior art in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the methods of the embodiments of the present invention. And the aforementioned storage medium includes: a removable storage device, ROM, RAM, magnetic or optical disk, or other medium capable of storing program code.
The foregoing is merely illustrative embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily think about variations or substitutions within the technical scope of the present invention, and the invention should be covered. Therefore, the protection scope of the invention is subject to the protection scope of the claims.