CN115358281B - Machine learning-based cold and hot all-in-one machine monitoring control method and system - Google Patents
Machine learning-based cold and hot all-in-one machine monitoring control method and system Download PDFInfo
- Publication number
- CN115358281B CN115358281B CN202211290190.6A CN202211290190A CN115358281B CN 115358281 B CN115358281 B CN 115358281B CN 202211290190 A CN202211290190 A CN 202211290190A CN 115358281 B CN115358281 B CN 115358281B
- Authority
- CN
- China
- Prior art keywords
- machine
- temperature
- information
- fault
- cold
- 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
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D23/00—Control of temperature
- G05D23/19—Control of temperature characterised by the use of electric means
- G05D23/1927—Control of temperature characterised by the use of electric means using a plurality of sensors
- G05D23/193—Control of temperature characterised by the use of electric means using a plurality of sensors sensing the temperaure in different places in thermal relationship with one or more spaces
- G05D23/1931—Control of temperature characterised by the use of electric means using a plurality of sensors sensing the temperaure in different places in thermal relationship with one or more spaces to control the temperature of one space
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N7/00—Computing arrangements based on specific mathematical models
- G06N7/02—Computing arrangements based on specific mathematical models using fuzzy logic
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C3/00—Registering or indicating the condition or the working of machines or other apparatus, other than vehicles
- G07C3/005—Registering or indicating the condition or the working of machines or other apparatus, other than vehicles during manufacturing process
Abstract
The invention discloses a machine learning-based cold and hot all-in-one machine monitoring control method and a system, wherein the method comprises the following steps: acquiring operation parameters of the cold and hot all-in-one machine, extracting a heating temperature curve and a cooling temperature curve according to the operation parameters, acquiring regional temperature information of a heating and cooling region to construct a regional environment temperature field, and acquiring an abnormal temperature region of a processing object according to the heating temperature curve and the cooling temperature curve through the regional environment temperature field; setting feedback information according to the abnormal temperature difference information of the abnormal temperature area, and correcting the output power of the cold-hot all-in-one machine through the feedback information; meanwhile, an operation state monitoring model and a fault diagnosis model are constructed based on machine learning, and an operation state and fault identification result of the cold and hot all-in-one machine is generated. The invention monitors abnormal temperature information in heating and cooling of the cold and hot all-in-one machine, corrects output power, realizes accurate temperature control, and simultaneously monitors the running state in real time to ensure the running safety of the cold and hot all-in-one machine.
Description
Technical Field
The invention relates to the technical field of industrial automation information monitoring, in particular to a machine learning-based cold and hot all-in-one machine monitoring control method and system.
Background
At present, in the fields of chemical industry and biotechnology industry, the temperature control process is distributed in the research and production amplification links, and the temperature control is very important for safe and high-quality reaction products. In order to obtain high-quality reaction products, the temperature control system needs to perform stable and reliable process temperature control on an external reaction kettle and processed products.
Cold and hot all-in-one can self-heating or refrigeration according to the industry demand as temperature control device commonly used in industrial production, and the organism divide into heating part and cooling part, and the organism can heat rapidly, the required temperature of cooling arrangement rapidly to can control the different temperatures of a plurality of surface ways, the rapid cycle improves production efficiency greatly around in the product forming process. The current cold and hot all-in-one machine can display fault codes, but cannot monitor abnormal conditions in the operation process, analyze the operation state and realize fault prediction and accurate positioning; therefore, a system needs to be developed to monitor the operation of the device at any time, actively report the current operation state, and adjust the control strategy according to the operation state to ensure the safe operation of the cooling and heating all-in-one machine, and how to monitor the operation state through a machine learning method in the implementation process is one of the problems that needs to be solved urgently.
Disclosure of Invention
In order to solve the technical problems, the invention provides a machine learning-based cold and hot all-in-one machine monitoring control method and system.
The invention provides a machine learning-based cold and hot all-in-one machine monitoring control method, which comprises the following steps:
acquiring operation parameters of the cold and hot all-in-one machine, and extracting a heating temperature curve and a cooling temperature curve according to the operation parameters;
acquiring the regional temperature information of a heating and cooling region, constructing a regional environment temperature field according to the regional temperature information, and acquiring an abnormal temperature region of a processing object according to the heating temperature curve and the cooling temperature curve through the regional environment temperature field;
setting feedback information according to the abnormal temperature difference information of the abnormal temperature area, and correcting the output power of the cold and hot integrated machine through the feedback information;
meanwhile, an operation state monitoring model and a fault diagnosis model are built based on machine learning, and operation parameters are input into the operation state monitoring model and the fault diagnosis model to generate an operation state and fault identification result of the cooling and heating all-in-one machine.
In this scheme, the abnormal temperature region of the processing object is obtained through the region environment temperature field according to the heating temperature curve and the cooling temperature curve, which specifically comprises:
acquiring a target heating temperature and a target cooling temperature of a target processing object, setting a target heating curve and a target cooling curve, dividing a heating and cooling area into a plurality of grid areas, and acquiring an area environment temperature field according to temperature information of each grid area;
acquiring real-time temperature information of each regional grating according to a regional environment temperature field to acquire a temperature difference with initial temperature information, and acquiring a temperature change rate of each regional grating according to the temperature difference;
acquiring a grating area with the temperature change rate larger than a preset temperature change rate threshold value as a key mark grating area, predicting temperature information after preset time according to the temperature change rate, and reading a heating temperature curve and a cooling temperature curve according to the temperature change rate and the temperature information;
and judging the matching degree of the heating temperature curve and the cooling temperature curve with the target heating curve and the target cooling curve, and taking the area grating with the matching degree smaller than a preset matching degree threshold value as an abnormal temperature area.
In this scheme, set up feedback information according to the regional unusual difference in temperature information of unusual temperature, set up the output of cold and hot all-in-one through feedback information, specifically do:
acquiring temperature information of an abnormal temperature area after preset time and target temperature information corresponding to the same moment in the target heating temperature or the target cooling temperature, and comparing the temperature information with the target temperature information to acquire abnormal temperature difference information;
acquiring the current flow speed and flow information of a heat transfer medium in the cold and hot all-in-one machine, and generating feedback information according to the corresponding relation between the temperature and the flow speed and flow of the heat transfer medium through abnormal temperature difference information;
and correcting the current flow speed and flow information of the heat transfer medium according to the feedback information, and acquiring the corrected output power to operate the target processing object.
In the scheme, the running state monitoring model is constructed based on machine learning, and the running parameters are input into the running state monitoring model to generate the running state of the cooling and heating all-in-one machine, specifically comprising the following steps:
acquiring operation parameters of the cold and hot all-in-one machine, denoising the operation parameters through wavelet transformation, and extracting characteristic signals of the operation parameters through empirical mode decomposition by using the denoised operation parameters;
matching the characteristic signal of the historical operating parameter of the cold and hot all-in-one machine with fault information, and representing the fault information of the cold and hot all-in-one machine through a reconstructed signal;
performing feature fusion on the feature signals of the operation parameters after empirical mode decomposition, and combining the feature signals with external environment factors based on preset expert experience to generate fusion features;
constructing a cold and hot all-in-one machine operation state detection model based on LSTM, inputting the fusion characteristics into a unit structure of the LSTM network, and outputting an operation state monitoring sequence of the cold and hot all-in-one machine after preset time;
and comparing the running state detection sequence after the preset time with the reference curve of each running parameter to obtain the running state of the cold and hot all-in-one machine.
In the scheme, fault identification is carried out according to the operation parameters of the cold and hot all-in-one machine through the fault diagnosis model, and the method specifically comprises the following steps:
acquiring parameter characteristics corresponding to each operating parameter, acquiring parameter information of preset data with the highest accumulated contribution degree through principal component analysis of each parameter characteristic, and taking the parameter information of a preset number as a principal component direction;
projecting the characteristic signals of the operating parameters to a principal component direction to obtain a characteristic scatter diagram under different fault information, and obtaining fault identification characteristics of the cold-hot all-in-one machine according to the characteristic scatter diagram;
constructing a fault diagnosis model based on a support vector machine, optimizing the support vector machine through a particle swarm algorithm, and outputting optimal support vector machine parameters;
acquiring historical characteristic signals matched with the fault information as training data, and training a fault diagnosis model according to the optimal support vector machine parameters and the training data;
and inputting the fault identification characteristics into a trained fault diagnosis model, and outputting fault identification information and fault position information of the cold-hot all-in-one machine.
In the scheme, the concurrent faults are predicted according to the running state of the cold and hot all-in-one machine and the incidence relation of each fault, and the method specifically comprises the following steps:
acquiring fault principle information of fault information based on big data retrieval, constructing a fault tree model of the cold and hot all-in-one machine according to the structural composition of the cold and hot all-in-one machine and the fault principle information, and constructing a Bayesian network model according to the logical relationship of the fault tree model;
acquiring occurrence frequency of different fault information through historical operating parameters to acquire prior probability of each fault node in the Bayesian network, and acquiring membership degree of each fault node to each preset evaluation interval according to a fuzzy comprehensive evaluation method;
acquiring an evaluation result of the prior probability of the fault nodes and an evaluation result of the joint probability and the conditional probability between the fault nodes according to the membership degree, the weight information corresponding to a preset evaluation interval and the weight information corresponding to the running state, wherein the preset evaluation interval reflects the severity of the fault;
when the fault of the target fault node occurs, the influence degree of the associated node is obtained according to the current running state of the cold-hot all-in-one machine and the evaluation result of the prior probability of the target fault node, and the concurrent fault information is obtained according to the influence degree.
The second aspect of the present invention also provides a machine learning-based monitoring and controlling system for a cold and hot all-in-one machine, which comprises: the monitoring and controlling method of the cold and hot all-in-one machine based on machine learning comprises a memory and a processor, wherein the memory comprises a program of the monitoring and controlling method of the cold and hot all-in-one machine based on machine learning, and when the program of the monitoring and controlling method of the cold and hot all-in-one machine based on machine learning is executed by the processor, the following steps are realized:
acquiring operation parameters of the cold and hot all-in-one machine, and extracting a heating temperature curve and a cooling temperature curve according to the operation parameters;
acquiring regional temperature information of a heating and cooling region, constructing a regional environment temperature field according to the regional temperature information, and acquiring an abnormal temperature region of a processing object according to the heating temperature curve and the cooling temperature curve through the regional environment temperature field;
setting feedback information according to the abnormal temperature difference information of the abnormal temperature area, and correcting the output power of the cold-hot all-in-one machine through the feedback information;
meanwhile, an operation state monitoring model and a fault diagnosis model are built based on machine learning, and operation parameters are input into the operation state monitoring model and the fault diagnosis model to generate an operation state and fault identification result of the cooling and heating all-in-one machine.
The invention discloses a machine learning-based cold and hot all-in-one machine monitoring control method and a system, which comprises the following steps: acquiring operation parameters of the cold and hot all-in-one machine, extracting a heating temperature curve and a cooling temperature curve according to the operation parameters, acquiring regional temperature information of a heating and cooling region, constructing a regional environment temperature field according to the regional temperature information, and acquiring an abnormal temperature region of a processing object according to the heating temperature curve and the cooling temperature curve through the regional environment temperature field; setting feedback information according to the abnormal temperature difference information of the abnormal temperature area, and setting the output power of the cold and hot all-in-one machine through the feedback information; meanwhile, an operation state monitoring model is built based on machine learning, and operation parameters are input into the operation state monitoring model to generate the operation state and fault identification and positioning of the cooling and heating integrated machine. The invention monitors abnormal temperature information in heating and cooling of the cold and hot all-in-one machine, corrects output power, realizes accurate temperature control, reduces the defect rate of products, monitors the running state and realizes quick analysis and positioning of faults. The operation and maintenance management of the cold and hot all-in-one machine is realized according to the quick location of the fault, and the stable operation of the cold and hot all-in-one machine is ensured, so that the enterprise culture production progress is accelerated, the energy consumption is reduced, the product forming efficiency is improved, the product defects are inhibited, the production of defective products is reduced, and the cost is low and the effect is high.
Drawings
FIG. 1 is a flow chart of a monitoring and controlling method of a cold and hot all-in-one machine based on machine learning according to the invention;
FIG. 2 is a flow chart of a method for generating an operating state of a cooling and heating all-in-one machine according to an operating state monitoring model;
FIG. 3 is a flow chart illustrating a method of fault identification from operating parameters by a fault diagnosis model in accordance with the present invention;
fig. 4 shows a block diagram of a monitoring control system of a cold and hot all-in-one machine based on machine learning.
Detailed Description
In order that the above objects, features and advantages of the present invention can be more clearly understood, a more particular description of the invention, taken in conjunction with the accompanying drawings and detailed description, is set forth below. It should be noted that the embodiments and features of the embodiments of the present application may be combined with each other without conflict.
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 specifically described herein, and therefore the scope of the present invention is not limited by the specific embodiments disclosed below.
Fig. 1 shows a flow chart of a monitoring and controlling method of a cooling and heating all-in-one machine based on machine learning according to the invention.
As shown in fig. 1, a first aspect of the present invention provides a machine learning-based monitoring and controlling method for a cold and hot all-in-one machine, including:
s102, acquiring operation parameters of the cold and hot integrated machine, and extracting a heating temperature curve and a cooling temperature curve according to the operation parameters;
s104, acquiring the regional temperature information of a heating and cooling region, constructing a regional environment temperature field according to the regional temperature information, and acquiring an abnormal temperature region of the processing object according to the heating temperature curve and the cooling temperature curve through the regional environment temperature field;
s106, setting feedback information according to the abnormal temperature difference information of the abnormal temperature area, and correcting the output power of the cold-hot all-in-one machine through the feedback information;
and S108, simultaneously, constructing an operation state monitoring model and a fault diagnosis model based on machine learning, and inputting operation parameters into the operation state monitoring model and the fault diagnosis model to generate an operation state and fault identification result of the cooling and heating all-in-one machine.
The operation parameters include, but are not limited to, temperature information, current and voltage information, vibration information, power information and other operation data of the cold and hot all-in-one machine, and the operation parameters are acquired through preset sensors arranged at different positions of the cold and hot all-in-one machine. This can result in distortion of the acquired signal due to the large amount of noise interference at the acquisition site. In order to eliminate adverse factors of an analysis result, the acquired data signals are subjected to preliminary filtering, and operation parameters of the preliminary filtering are obtained.
The obtaining of the abnormal temperature region of the processing object according to the heating temperature curve and the cooling temperature curve through the region ambient temperature field specifically includes: acquiring a target heating temperature and a target cooling temperature of a target processing object, setting a target heating curve and a target cooling curve, dividing a heating and cooling area into a plurality of grid areas, and acquiring an area environment temperature field according to temperature information of each grid area; acquiring real-time temperature information of each regional grid according to a regional environment temperature field to acquire a temperature difference with initial temperature information, and acquiring a temperature change rate of each regional grid according to the temperature difference; acquiring a grating area with the temperature change rate larger than a preset temperature change rate threshold value as a key mark grating area, predicting temperature information after preset time according to the temperature change rate, and reading a heating temperature curve and a cooling temperature curve according to the temperature change rate and the temperature information; and judging the matching degree of the heating curve and the cooling temperature curve with the target heating curve and the target cooling curve, and taking the area grating with the matching degree smaller than a preset matching degree threshold value as an abnormal temperature area.
The heating and cooling system in the cooling and heating integrated machine adopts a heat exchanger, usually adopts a coil or a jacket to indirectly control the temperature, and is simple and convenient, the jacket is provided with heat conduction oil, cooling water or other heat transfer media, and the common heat transfer media include two types, namely heat conduction oil and water, which are used at different temperatures, and the temperature control of different heat transfer media is realized according to the corresponding relation between the water flow and flow speed information and the temperature, wherein feedback information is set according to abnormal temperature difference information of an abnormal temperature area, and the output power of the cooling and heating integrated machine is set through the feedback information, and the method specifically comprises the following steps: acquiring temperature information of an abnormal temperature area after preset time and target temperature information corresponding to the same moment in the target heating temperature or the target cooling temperature, and comparing the temperature information with the target temperature information to acquire abnormal temperature difference information; acquiring the current flow speed and flow information of a heat transfer medium in the cold and hot all-in-one machine, and generating feedback information according to the corresponding relation between the temperature and the flow speed and flow of the heat transfer medium through abnormal temperature difference information; and correcting the current flow speed and flow information of the heat transfer medium according to the feedback information, and acquiring the corrected output power to operate the target processing object.
FIG. 2 is a flow chart of a method for generating an operation state of a cooling and heating all-in-one machine according to an operation state monitoring model.
According to the embodiment of the invention, the running state monitoring model is constructed based on machine learning, and the running parameters are input into the running state monitoring model to generate the running state of the cold and hot all-in-one machine, which specifically comprises the following steps:
s202, acquiring operation parameters of the cooling and heating integrated machine, denoising the operation parameters through wavelet transformation, and extracting characteristic signals of the operation parameters through empirical mode decomposition by using the denoised operation parameters;
s204, matching the historical operating parameter characteristic signals of the cold and hot all-in-one machine with fault information, and representing the fault information of the cold and hot all-in-one machine through the reconstructed signals;
s206, performing feature fusion on the feature signals of the operation parameters after the empirical mode decomposition, and combining the feature signals with external environment factors based on preset expert experience to generate fusion features;
s208, constructing a cold and hot all-in-one machine operation condition detection model based on the LSTM, inputting the fusion characteristics into a unit structure of the LSTM network, and outputting an operation state monitoring sequence of the cold and hot all-in-one machine after preset time;
and S210, comparing the running state detection sequence after the preset time with the reference curve of each running parameter to obtain the running state of the cold and hot all-in-one machine.
The model structure of the detection model for the operation state of the cooling and heating all-in-one machine is an input layer, a feature fusion layer, an LSTM unit structure layer, a full connection layer and an output layer, wherein a preprocessed operation parameter feature signal is input into the input layer, feature fusion is performed through the feature fusion layer, environmental features are added into the fusion features, the fusion features are input into the LSTM unit structure layer by considering the influence of the environment on the operation state of the cooling and heating all-in-one machine, the LSTM unit structure mainly controls the transmission state through a forgetting gate, a memory gate and an output gate, finally, the output dimension is converted into the time step number of preset time through the full connection layer, and the output layer outputs the operation state of the cooling and heating all-in-one machine after the preset time.
FIG. 3 is a flow chart illustrating a method for fault identification based on operating parameters via a fault diagnosis model according to the present invention.
According to the embodiment of the invention, the fault diagnosis model is used for carrying out fault identification according to the operation parameters of the cold and hot all-in-one machine, and the method specifically comprises the following steps:
s302, obtaining parameter characteristics corresponding to each operation parameter, obtaining parameter information of preset data with the highest accumulated contribution degree through principal component analysis of each parameter characteristic, and taking the parameter information of the preset number as a principal component direction;
s304, projecting the characteristic signals of the operation parameters to the principal component direction to obtain a characteristic scatter diagram under different fault information, and obtaining fault identification characteristics of the cold-hot all-in-one machine according to the characteristic scatter diagram;
s306, constructing a fault diagnosis model based on the support vector machine, optimizing the support vector machine through a particle swarm algorithm, and outputting optimal support vector machine parameters;
s308, acquiring historical characteristic signals matched with the fault information as training data, and training a fault diagnosis model according to the parameters of the optimal support vector machine and the training data;
and S310, inputting the fault identification characteristics into a trained fault diagnosis model, and outputting fault identification information and fault position information of the cold and hot all-in-one machine.
The method includes the steps that operation parameter types with the largest contribution degree to fault information are obtained through principal component analysis according to operation parameters, and selected operation parameters are subjected to feature clustering under different fault types through a feature scatter diagram mode, wherein the optimal parameters of a support vector machine are obtained through a particle swarm algorithm, particle populations are initialized, particle speed and position information are given randomly, an integral performance index is adopted as an optimization target function, the integral performance index is calculated according to the positions of the particles to obtain the fitness of each particle, the advantages and the disadvantages of the particles are judged according to the fitness value, if the constraints are not met, the particles are removed, and iterative training is carried out on the removed particles until the constraints are met; after updating the particle speed and position information for a plurality of times, judging whether the maximum iteration times or the ideal group optimal fitness value is reached, finishing the operation if the conditions are met, outputting an optimal result to obtain the optimal position searched by each particle and the optimal positions in all the particles, and outputting the optimal parameter factor of the support vector machine.
It should be noted that the concurrent faults are predicted according to the running state of the cooling and heating all-in-one machine and the incidence relation of each fault, and specifically the method comprises the following steps: acquiring fault principle information of fault information based on big data retrieval, constructing a fault tree model of the cold and hot all-in-one machine according to the structural composition of the cold and hot all-in-one machine and the fault principle information, and constructing a Bayesian network model according to a logical relation of faults in the fault tree model, wherein the logical relation is used for detecting the suction temperature of a compressor copper pipe when the cold and hot all-in-one machine is cooled, and if the temperature is too low, the water flow is insufficient, the cooling effect is not ideal due to insufficient water flow, and the quality of a processed object is influenced; acquiring occurrence frequency of different fault information through historical operating parameters to acquire prior probability of each fault node in a Bayesian network, determining evaluation intervals, wherein each evaluation interval corresponds to different severity of a fault, presetting weight information for each evaluation interval, acquiring membership of each fault node to each preset evaluation interval according to a fuzzy comprehensive evaluation method, and describing the occurrence probability of the fault and the degree of influence between the faults through different membership; acquiring an evaluation result of prior probability of fault nodes and an evaluation result of joint probability and conditional probability between the fault nodes according to the membership and the weight information corresponding to a preset evaluation interval and the weight information corresponding to the running state by adopting a maximum membership principle, wherein the preset evaluation interval reflects the severity of the fault; the calculation formula of the condition profile between the fault nodes and the influence degree between the fault nodes is specifically as follows:
wherein, the first and the second end of the pipe are connected with each other,indicating a failed nodeAndthe results of evaluation of the condition profiles therebetween,indicating a failed nodeAndthe result of evaluating the severity of the effect therebetween,weight information indicating a correspondence of the operation state,the number of items representing the evaluation interval,indicates the total number of evaluation intervals,is shown asThe weight information corresponding to each evaluation interval,is shown asFault in each evaluation intervalCause a failureDegree of membership occurred;
when the fault of the target fault node occurs, the influence degree of the associated node is obtained according to the current running state of the cold-hot all-in-one machine and the evaluation result of the prior probability of the target fault node, and the concurrent fault information is obtained according to the influence degree.
It should be noted that, in the operation state and fault identification monitoring of the cooling and heating integrated machine, the system also comprises a cloud service system, the GSM, GPRS and 3G communication modules read the device information through the communication interface, the user can directly control the device to be turned on and off, set the temperature and inquire the current temperature through the short message of the mobile phone, and when the device fails, the system can automatically send information to the designated mobile phone user; and the running state of the equipment can be directly inquired by logging in the cloud server through the internet-surfing computer.
According to the embodiment of the invention, a heating and refrigerating data database of the cold and hot all-in-one machine is constructed, and the method specifically comprises the following steps:
a heating and refrigerating data database of the cold and hot all-in-one machine is established, heating and refrigerating data of historical processing objects with different models and specifications are stored in the database, and heating curves and refrigerating curves of the historical processing objects are matched with the occurrence conditions of abnormal temperature areas;
when the occurrence frequency of abnormal temperature areas at the same target temperature is greater than a preset threshold value, performing curve fitting on the heating curves and the refrigeration curves corresponding to different abnormal temperature areas after power correction to generate new target heating curves and target refrigeration curves to replace the original target heating curves and target refrigeration curves and store the new target heating curves and the target refrigeration curves in a heating and refrigeration database of the integrated cooling and heating machine;
establishing a retrieval tag according to a current processing object, carrying out similarity comparison in a heating and refrigerating database through the retrieval tag, acquiring heating and refrigerating data of a historical processing object with the similarity meeting the requirement of a preset value, and acquiring a target heating curve and a target refrigerating curve according to the heating and refrigerating data;
if the current processing object has a temperature abnormal area, generating abnormal characteristics according to the abnormal temperature difference information and the area grating information of the abnormal area, carrying out similarity comparison in the heating and refrigerating data of the historical processing object according to the abnormal characteristics, and directly extracting a corresponding target heating curve and a corresponding target refrigerating curve in the heating and refrigerating data with the maximum similarity.
It should be noted that, the solution of the historical fault is stored in the database, when a system fault is detected in the cold and hot integrated machine, fault information is determined according to the running report, the running report is compared with the historical fault data in the database to generate a comparison similarity, and a comparison similarity threshold is preset; when the contrast similarity is larger than or equal to the contrast similarity threshold, marking the historical fault data, and aggregating the marked historical fault data to generate a similar historical fault data set; analyzing the fault information according to the operation records in the similar historical fault data set to generate a solution; and if the contrast similarity between the historical fault data and the running report in the database is smaller than the contrast similarity threshold, updating the original data in the database according to the fault information.
FIG. 4 shows a block diagram of a monitoring and controlling system of a cold and hot all-in-one machine based on machine learning.
The second aspect of the present invention also provides a machine learning-based monitoring and controlling system 4 for a cold and hot all-in-one machine, which comprises: a memory 41 and a processor 42, where the memory includes a program of a machine learning-based monitoring and controlling method for a cooling and heating all-in-one machine, and when executed by the processor, the program of the machine learning-based monitoring and controlling method for a cooling and heating all-in-one machine implements the following steps:
acquiring operation parameters of the cold and hot all-in-one machine, and extracting a heating temperature curve and a cooling temperature curve according to the operation parameters;
acquiring the regional temperature information of a heating and cooling region, constructing a regional environment temperature field according to the regional temperature information, and acquiring an abnormal temperature region of a processing object according to the heating temperature curve and the cooling temperature curve through the regional environment temperature field;
setting feedback information according to the abnormal temperature difference information of the abnormal temperature area, and correcting the output power of the cold-hot all-in-one machine through the feedback information;
meanwhile, an operation state monitoring model and a fault diagnosis model are built based on machine learning, and operation parameters are input into the operation state monitoring model and the fault diagnosis model to generate an operation state and fault identification result of the cooling and heating all-in-one machine.
The operation parameters include, but are not limited to, temperature information, current and voltage information, vibration information, power information and other operation data of the cold and hot all-in-one machine, and the operation parameters are acquired through preset sensors arranged at different parts of the cold and hot all-in-one machine. This can result in distortion of the acquired signal due to the large amount of noise interference at the acquisition site. In order to eliminate adverse factors of an analysis result, the acquired data signals are subjected to preliminary filtering, and operation parameters of the preliminary filtering are obtained.
The obtaining of the abnormal temperature region of the processing object according to the heating temperature curve and the cooling temperature curve through the region ambient temperature field specifically includes: acquiring a target heating temperature and a target cooling temperature of a target processing object, setting a target heating curve and a target cooling curve, dividing a heating and cooling area into a plurality of grid areas, and acquiring an area environment temperature field according to temperature information of each grid area; acquiring real-time temperature information of each regional grid according to a regional environment temperature field to acquire a temperature difference with initial temperature information, and acquiring a temperature change rate of each regional grid according to the temperature difference; acquiring a grating area with the temperature change rate larger than a preset temperature change rate threshold value as a key mark grating area, predicting temperature information after preset time according to the temperature change rate, and reading a heating temperature curve and a cooling temperature curve according to the temperature change rate and the temperature information; and judging the matching degree of the heating curve and the cooling temperature curve with the target heating curve and the target cooling curve, and taking the area grating with the matching degree smaller than a preset matching degree threshold value as an abnormal temperature area.
The heating and cooling system in the cooling and heating integrated machine adopts a heat exchanger, usually adopts a coil or a jacket to indirectly control the temperature, and is simple and convenient, the jacket is provided with heat conduction oil, cooling water or other heat transfer media, and the common heat transfer media include two types, namely heat conduction oil and water, which are used at different temperatures, and the temperature control of different heat transfer media is realized according to the corresponding relation between the water flow and flow speed information and the temperature, wherein feedback information is set according to abnormal temperature difference information of an abnormal temperature area, and the output power of the cooling and heating integrated machine is set through the feedback information, and the method specifically comprises the following steps: acquiring temperature information of an abnormal temperature area after preset time and target temperature information corresponding to the same moment in the target heating temperature or the target cooling temperature, and comparing the temperature information with the target temperature information to acquire abnormal temperature difference information; acquiring the current flow speed and flow information of a heat transfer medium in the cold and hot all-in-one machine, and generating feedback information according to the corresponding relation between the temperature and the flow speed and flow of the heat transfer medium through abnormal temperature difference information; and correcting the current flow speed and flow information of the heat transfer medium according to the feedback information, and acquiring the corrected output power to operate the target processing object.
According to the embodiment of the invention, the running state monitoring model is constructed based on machine learning, and the running parameters are input into the running state monitoring model to generate the running state of the cold and hot all-in-one machine, which specifically comprises the following steps:
acquiring operation parameters of the cooling and heating integrated machine, denoising the operation parameters through wavelet transformation, and extracting characteristic signals of the operation parameters through empirical mode decomposition by using the denoised operation parameters;
matching the characteristic signal of the historical operating parameter of the cold and hot all-in-one machine with fault information, and representing the fault information of the cold and hot all-in-one machine through a reconstructed signal;
performing feature fusion on the feature signals of the operation parameters after the empirical mode decomposition, and combining the feature signals with external environment factors based on preset expert experience to generate fusion features;
constructing a cold and hot all-in-one machine operation state detection model based on LSTM, inputting the fusion characteristics into a unit structure of the LSTM network, and outputting an operation state monitoring sequence of the cold and hot all-in-one machine after preset time;
and comparing the running state detection sequence after the preset time with the reference curve of each running parameter to obtain the running state of the cold and hot all-in-one machine.
The model structure of the detection model for the operation state of the cooling and heating all-in-one machine is an input layer, a feature fusion layer, an LSTM unit structure layer, a full connection layer and an output layer, wherein a preprocessed operation parameter feature signal is input into the input layer, feature fusion is performed through the feature fusion layer, environmental features are added into the fusion features, the fusion features are input into the LSTM unit structure layer by considering the influence of the environment on the operation state of the cooling and heating all-in-one machine, the LSTM unit structure mainly controls the transmission state through a forgetting gate, a memory gate and an output gate, finally, the output dimension is converted into the time step number of preset time through the full connection layer, and the output layer outputs the operation state of the cooling and heating all-in-one machine after the preset time.
According to the embodiment of the invention, the fault diagnosis model is used for carrying out fault identification according to the operation parameters of the cold and hot all-in-one machine, and the method specifically comprises the following steps:
acquiring parameter characteristics corresponding to each operating parameter, acquiring parameter information of preset data with the highest accumulated contribution degree through principal component analysis of each parameter characteristic, and taking the parameter information of a preset number as a principal component direction;
projecting the characteristic signals of the operating parameters to a principal component direction to obtain a characteristic scatter diagram under different fault information, and obtaining fault identification characteristics of the cold-hot all-in-one machine according to the characteristic scatter diagram;
constructing a fault diagnosis model based on a support vector machine, optimizing the support vector machine through a particle swarm algorithm, and outputting optimal support vector machine parameters;
acquiring historical characteristic signals matched with the fault information as training data, and training a fault diagnosis model according to the optimal support vector machine parameters and the training data;
and inputting the fault identification characteristics into a trained fault diagnosis model, and outputting fault identification information and fault position information of the cold and hot all-in-one machine.
The method comprises the steps of obtaining an operation parameter type with the largest contribution degree to fault information through principal component analysis according to operation parameters, and realizing feature clustering of the selected operation parameters under different fault categories in a feature scatter diagram mode, wherein the optimal parameters of a support vector machine are obtained through a particle swarm algorithm, particle populations are initialized, particle speed and position information are randomly given, an integral performance index is adopted as an optimization target function, the integral performance index is calculated according to the positions of the particles to obtain the fitness of each particle, whether the particles are good or bad is judged according to the fitness value, if the constraints are not met, the particles are removed, and iterative training is carried out on the removed particles until the constraints are met; after updating the particle speed and position information for a plurality of times, judging whether the maximum iteration times or the ideal group optimal fitness value is reached, finishing the operation if the conditions are met, outputting an optimal result to obtain the optimal position searched by each particle and the optimal positions in all the particles, and outputting the optimal parameter factor of the support vector machine.
It should be noted that the concurrent faults are predicted according to the running state of the cooling and heating all-in-one machine and the incidence relation of each fault, and the specific steps are as follows: acquiring fault principle information of fault information based on big data retrieval, constructing a fault tree model of the cold and hot all-in-one machine according to the structural composition of the cold and hot all-in-one machine and the fault principle information, and constructing a Bayesian network model according to a logical relation of faults in the fault tree model, wherein the logical relation is used for detecting the suction temperature of a compressor copper pipe when the cold and hot all-in-one machine is cooled, and if the temperature is too low, the water flow is insufficient, so that the cooling effect is not ideal due to insufficient water flow, and the quality of a processed object is influenced; acquiring occurrence frequency of different fault information through historical operation parameters to acquire prior probability of each fault node in a Bayesian network, determining evaluation intervals, wherein each evaluation interval corresponds to different severity degrees of faults, presetting weight information for each evaluation interval, acquiring membership of each fault node to each preset evaluation interval according to a fuzzy comprehensive evaluation method, and describing occurrence probability of the faults and degree of influence between the faults through different membership degrees; acquiring an evaluation result of prior probability of fault nodes and an evaluation result of joint probability and conditional probability between the fault nodes according to the membership and the weight information corresponding to a preset evaluation interval and the weight information corresponding to an operating state by adopting a maximum membership principle, wherein the preset evaluation interval reflects the severity of the fault; the calculation formula of the condition profile between the fault nodes and the influence degree between the fault nodes is specifically as follows:
wherein the content of the first and second substances,indicating failed nodesAndthe result of evaluation of the condition profile in (2),indicating a failed nodeAndthe result of evaluating the severity of the effect therebetween,weight information indicating a correspondence of the operation state,the number of items representing the evaluation interval,indicates the total number of evaluation intervals,is shown asThe weight information corresponding to each evaluation interval,denotes the firstFault in each evaluation intervalCause a failureDegree of membership occurred;
when the fault of the target fault node occurs, the influence degree of the associated node is obtained according to the current running state of the cold-hot all-in-one machine and the evaluation result of the prior probability of the target fault node, and the concurrent fault information is obtained according to the influence degree.
It should be noted that, in the operation state and fault identification monitoring of the cooling and heating integrated machine, the system also comprises a cloud service system, the GSM, GPRS and 3G communication modules read the device information through the communication interface, and the user can directly control the device to be turned on and off, set the temperature and inquire the current temperature through the short message of the mobile phone, and when the device fails, the user can automatically send information to the designated mobile phone user; and the running state of the equipment can be directly inquired by logging in the cloud server through the internet-surfing computer.
In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above-described device embodiments are merely illustrative, for example, the division of the unit is only one logical function division, and there may be other division ways in actual implementation, such as: multiple units or components may be combined, or may be integrated into another system, or some features may be omitted, or not implemented. In addition, the coupling, direct coupling or communication connection between the components shown or discussed may be through some interfaces, and the indirect coupling or communication connection between the devices or units may be electrical, mechanical or other forms.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units; can be located in one place or distributed on a plurality of network units; some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as one unit, or two or more units may be integrated into one unit; the integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional unit.
Those of ordinary skill in the art will understand that: all or part of the steps for realizing the method embodiments can be completed by hardware related to program instructions, the program can be stored in a computer readable storage medium, and the program executes the steps comprising the method embodiments when executed; and the aforementioned storage medium includes: a mobile storage device, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and various media capable of storing program codes.
Alternatively, the integrated unit of the present invention may be stored in a computer-readable storage medium if it is implemented in the form of a software functional module and sold or used as a separate product. Based on such understanding, the technical solutions of the embodiments of the present invention may be essentially implemented or a part contributing to the prior art may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the methods described in the embodiments of the present invention. And the aforementioned storage medium includes: a removable storage device, a ROM, a RAM, a magnetic or optical disk, or various other media that can store program code.
The above description is only for the specific 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 conceive of the changes or substitutions within the technical scope of the present invention, and all the changes or substitutions should be covered within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the appended claims.
Claims (5)
1. A cold and hot all-in-one machine monitoring control method based on machine learning is characterized by comprising the following steps:
acquiring operation parameters of the cold and hot all-in-one machine, and extracting a heating temperature curve and a cooling temperature curve according to the operation parameters;
acquiring regional temperature information of a heating and cooling region, constructing a regional environment temperature field according to the regional temperature information, and acquiring an abnormal temperature region of a processing object according to the heating temperature curve and the cooling temperature curve through the regional environment temperature field;
setting feedback information according to the abnormal temperature difference information of the abnormal temperature area, and correcting the output power of the cold-hot all-in-one machine through the feedback information;
meanwhile, an operation state monitoring model and a fault diagnosis model are built based on machine learning, and operation parameters are input into the operation state monitoring model and the fault diagnosis model to generate an operation state and a fault identification result of the cooling and heating all-in-one machine;
an operation state monitoring model is constructed based on machine learning, and operation parameters are input into the operation state monitoring model to generate the operation state of the cold and hot all-in-one machine, and the method specifically comprises the following steps:
acquiring operation parameters of the cold and hot all-in-one machine, denoising the operation parameters through wavelet transformation, and extracting characteristic signals of the operation parameters through empirical mode decomposition by using the denoised operation parameters;
matching the characteristic signal of the historical operating parameter of the cold and hot all-in-one machine with fault information, and representing the fault information of the cold and hot all-in-one machine through a reconstructed signal;
performing feature fusion on the feature signals of the operation parameters after the empirical mode decomposition, and combining the feature signals with external environment factors based on preset expert experience to generate fusion features;
constructing a cold and hot all-in-one machine operation state detection model based on LSTM, inputting the fusion characteristics into a unit structure of the LSTM network, and outputting an operation state monitoring sequence of the cold and hot all-in-one machine after preset time;
comparing the running state detection sequence after the preset time with the reference curve of each running parameter to obtain the running state of the cold-hot all-in-one machine;
the fault diagnosis model is used for identifying faults according to the operation parameters of the cold and hot all-in-one machine, and the method specifically comprises the following steps:
acquiring parameter characteristics corresponding to each operating parameter, acquiring parameter information of preset data with the highest accumulated contribution degree through principal component analysis of each parameter characteristic, and taking the parameter information of preset quantity as a principal component direction;
projecting the characteristic signals of the operating parameters to a principal component direction to obtain a characteristic scatter diagram under different fault information, and obtaining fault identification characteristics of the cold-hot all-in-one machine according to the characteristic scatter diagram;
constructing a fault diagnosis model based on a support vector machine, optimizing the support vector machine through a particle swarm algorithm, and outputting optimal support vector machine parameters;
acquiring historical characteristic signals matched with fault information as training data, and training a fault diagnosis model according to optimal support vector machine parameters and the training data;
inputting the fault identification characteristics into a trained fault diagnosis model, and outputting fault identification information and fault position information of the cold and hot all-in-one machine;
predicting concurrent faults according to the running state of the cold and hot all-in-one machine and the incidence relation of the faults, and specifically comprising the following steps:
acquiring fault principle information of fault information based on big data retrieval, constructing a fault tree model of the cold and hot all-in-one machine according to the structural composition of the cold and hot all-in-one machine and the fault principle information, and constructing a Bayesian network model according to the logical relationship of the fault tree model;
acquiring occurrence frequency of different fault information through historical operating parameters to acquire prior probability of each fault node in the Bayesian network, and acquiring membership degree of each fault node to each preset evaluation interval according to a fuzzy comprehensive evaluation method;
acquiring an evaluation result of the prior probability of the fault nodes and an evaluation result of the joint probability and the conditional probability between the fault nodes according to the membership degree, the weight information corresponding to a preset evaluation interval and the weight information corresponding to the running state, wherein the preset evaluation interval reflects the severity of the fault;
when the fault of the target fault node occurs, the influence degree of the associated node is obtained according to the current running state of the cold-hot all-in-one machine and the evaluation result of the prior probability of the target fault node, and the concurrent fault information is obtained according to the influence degree.
2. The machine learning-based cooling and heating all-in-one machine monitoring control method is characterized in that an abnormal temperature region of a processing object is obtained through a region environment temperature field according to the heating temperature curve and the cooling temperature curve, and specifically comprises the following steps:
acquiring a target heating temperature and a target cooling temperature of a target processing object, setting a target heating curve and a target cooling curve, dividing a heating and cooling area into a plurality of grid areas, and acquiring an area environment temperature field according to temperature information of each grid area;
acquiring real-time temperature information of each regional grating according to a regional environment temperature field to acquire a temperature difference with initial temperature information, and acquiring a temperature change rate of each regional grating according to the temperature difference;
acquiring a grating area with the temperature change rate larger than a preset temperature change rate threshold value as a key mark grating area, predicting temperature information after preset time according to the temperature change rate, and reading a heating temperature curve and a cooling temperature curve according to the temperature change rate and the temperature information;
and judging the matching degree of the heating temperature curve and the cooling temperature curve with the target heating curve and the target cooling curve, and taking the area grating with the matching degree smaller than a preset matching degree threshold value as an abnormal temperature area.
3. The machine learning-based cooling and heating all-in-one machine monitoring control method according to claim 1, characterized in that feedback information is set according to abnormal temperature difference information of an abnormal temperature region, and the output power of the cooling and heating all-in-one machine is corrected through the feedback information, specifically:
acquiring temperature information of an abnormal temperature area after preset time and target temperature information corresponding to the same moment in the target heating temperature or the target cooling temperature, and comparing the temperature information with the target temperature information to acquire abnormal temperature difference information;
acquiring the current flow speed and flow information of a heat transfer medium in the cold and heat all-in-one machine, and generating feedback information according to the corresponding relation between the temperature and the flow speed and flow of the heat transfer medium through abnormal temperature difference information;
and correcting the current flow speed and flow information of the heat transfer medium according to the feedback information, and acquiring the corrected output power to operate the target processing object.
4. The utility model provides a cold and hot all-in-one monitor control system based on machine learning which characterized in that, this system includes: the monitoring and controlling method for the cold and hot all-in-one machine based on the machine learning comprises a memory and a processor, wherein the memory comprises a program of the monitoring and controlling method for the cold and hot all-in-one machine based on the machine learning, and when the program of the monitoring and controlling method for the cold and hot all-in-one machine based on the machine learning is executed by the processor, the following steps are realized:
acquiring operation parameters of the cold and hot all-in-one machine, and extracting a heating temperature curve and a cooling temperature curve according to the operation parameters;
acquiring the regional temperature information of a heating and cooling region, constructing a regional environment temperature field according to the regional temperature information, and acquiring an abnormal temperature region of a processing object according to the heating temperature curve and the cooling temperature curve through the regional environment temperature field;
setting feedback information according to the abnormal temperature difference information of the abnormal temperature area, and correcting the output power of the cold-hot all-in-one machine through the feedback information;
meanwhile, an operation state monitoring model and a fault diagnosis model are established based on machine learning, and operation parameters are input into the operation state monitoring model and the fault diagnosis model to generate an operation state and a fault identification result of the cooling and heating integrated machine;
an operation state monitoring model is built based on machine learning, operation parameters are input into the operation state monitoring model to generate an operation state of the cold and hot all-in-one machine, and the method specifically comprises the following steps:
acquiring operation parameters of the cooling and heating integrated machine, denoising the operation parameters through wavelet transformation, and extracting characteristic signals of the operation parameters through empirical mode decomposition by using the denoised operation parameters;
matching the characteristic signals of the historical operating parameters of the cold and hot integrated machine with fault information, and representing the fault information of the cold and hot integrated machine through the reconstructed signals;
performing feature fusion on the feature signals of the operation parameters after the empirical mode decomposition, and combining the feature signals with external environment factors based on preset expert experience to generate fusion features;
constructing a cold and hot all-in-one machine running state detection model based on LSTM, inputting the fusion characteristics into a unit structure of the LSTM network, and outputting a running state monitoring sequence of the cold and hot all-in-one machine after preset time;
comparing the running state detection sequence after the preset time with the reference curve of each running parameter to obtain the running state of the cold-hot all-in-one machine;
carrying out fault identification according to the operation parameters of the cold and hot all-in-one machine through a fault diagnosis model, which specifically comprises the following steps:
acquiring parameter characteristics corresponding to each operating parameter, acquiring parameter information of preset data with the highest accumulated contribution degree through principal component analysis of each parameter characteristic, and taking the parameter information of a preset number as a principal component direction;
projecting the characteristic signals of the operating parameters to a principal component direction to obtain a characteristic scatter diagram under different fault information, and obtaining fault identification characteristics of the cold-hot all-in-one machine according to the characteristic scatter diagram;
constructing a fault diagnosis model based on a support vector machine, optimizing the support vector machine through a particle swarm algorithm, and outputting optimal support vector machine parameters;
acquiring historical characteristic signals matched with the fault information as training data, and training a fault diagnosis model according to the optimal support vector machine parameters and the training data;
inputting the fault identification characteristics into a trained fault diagnosis model, and outputting fault identification information and fault position information of the cold-hot all-in-one machine;
predicting concurrent faults according to the running state of the cold and hot all-in-one machine and the incidence relation of the faults, and specifically comprising the following steps:
acquiring fault principle information of fault information based on big data retrieval, constructing a fault tree model of the cold and hot all-in-one machine according to the structural composition of the cold and hot all-in-one machine and the fault principle information, and constructing a Bayesian network model according to the logical relationship of the fault tree model;
acquiring occurrence frequency of different fault information through historical operating parameters to acquire prior probability of each fault node in the Bayesian network, and acquiring membership degree of each fault node to each preset evaluation interval according to a fuzzy comprehensive evaluation method;
acquiring an evaluation result of the prior probability of the fault nodes and an evaluation result of the joint probability and the conditional probability between the fault nodes according to the membership degree, the weight information corresponding to a preset evaluation interval and the weight information corresponding to the running state, wherein the preset evaluation interval reflects the severity of the fault;
when the fault of the target fault node occurs, the influence degree of the associated node is obtained according to the current running state of the cold-hot all-in-one machine and the evaluation result of the prior probability of the target fault node, and the concurrent fault information is obtained according to the influence degree.
5. The machine learning-based cooling and heating all-in-one machine monitoring and control system according to claim 4, wherein an abnormal temperature region of the processing object is obtained through a region ambient temperature field according to the heating temperature curve and the cooling temperature curve, and specifically comprises:
acquiring a target heating temperature and a target cooling temperature of a target processing object, setting a target heating curve and a target cooling curve, dividing a heating and cooling area into a plurality of grid areas, and acquiring an area environment temperature field according to temperature information of each grid area;
acquiring real-time temperature information of each regional grating according to a regional environment temperature field to acquire a temperature difference with initial temperature information, and acquiring a temperature change rate of each regional grating according to the temperature difference;
acquiring a grating area with the temperature change rate larger than a preset temperature change rate threshold value as a key mark grating area, predicting temperature information after preset time according to the temperature change rate, and reading a heating temperature curve and a cooling temperature curve according to the temperature change rate and the temperature information;
and judging the matching degree of the heating temperature curve and the cooling temperature curve with the target heating curve and the target cooling curve, and taking the area grating with the matching degree smaller than a preset matching degree threshold value as an abnormal temperature area.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211290190.6A CN115358281B (en) | 2022-10-21 | 2022-10-21 | Machine learning-based cold and hot all-in-one machine monitoring control method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211290190.6A CN115358281B (en) | 2022-10-21 | 2022-10-21 | Machine learning-based cold and hot all-in-one machine monitoring control method and system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN115358281A CN115358281A (en) | 2022-11-18 |
CN115358281B true CN115358281B (en) | 2023-01-13 |
Family
ID=84008303
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211290190.6A Active CN115358281B (en) | 2022-10-21 | 2022-10-21 | Machine learning-based cold and hot all-in-one machine monitoring control method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115358281B (en) |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115877890B (en) * | 2023-02-15 | 2023-05-12 | 广州志橙半导体有限公司 | Temperature control method and system for CVD equipment |
CN117505811B (en) * | 2024-01-08 | 2024-04-05 | 北京适创科技有限公司 | Die temperature control method and related device |
CN117554109B (en) * | 2024-01-11 | 2024-03-26 | 张家港长寿工业设备制造有限公司 | Intelligent monitoring method and system for fault data information of heat exchanger |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109657797A (en) * | 2018-12-24 | 2019-04-19 | 中国人民解放军32181部队 | Trouble diagnosibility analysis method based on hybrid diagnosis Bayesian network |
CN110411510A (en) * | 2019-07-18 | 2019-11-05 | 国家电网有限公司 | A kind of calculation method for excavating transformer station high-voltage side bus potentiality |
CN113077172A (en) * | 2021-04-19 | 2021-07-06 | 瑞湖智科数据(苏州)有限公司 | Equipment state trend analysis and fault diagnosis method |
CN113505448A (en) * | 2021-06-09 | 2021-10-15 | 上海电力大学 | Wind turbine generator dynamic reliability evaluation method based on improved Bayesian network |
CN114237155A (en) * | 2022-02-24 | 2022-03-25 | 深圳市正和楚基科技有限公司 | Error prediction and compensation method, system and medium for multi-axis numerical control machining |
CN114496693A (en) * | 2020-11-11 | 2022-05-13 | 中微半导体设备(上海)股份有限公司 | Multi-zone heating device, lower electrode assembly, plasma processing device and temperature adjusting method |
Family Cites Families (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101216715B (en) * | 2008-01-11 | 2010-06-09 | 宁波大学 | PID control temperature instrument using nerve cell network adjustment parameter and its control method |
WO2016033247A2 (en) * | 2014-08-26 | 2016-03-03 | Mtelligence Corporation | Population-based learning with deep belief networks |
DE102016008987B4 (en) * | 2015-07-31 | 2021-09-16 | Fanuc Corporation | Machine learning method and machine learning apparatus for learning failure conditions, and failure prediction apparatus and failure prediction system including the machine learning apparatus |
CN111351664B (en) * | 2020-02-13 | 2022-02-01 | 成都运达科技股份有限公司 | Bearing temperature prediction and alarm diagnosis method based on LSTM model |
CN112084910A (en) * | 2020-08-28 | 2020-12-15 | 北京旋极信息技术股份有限公司 | Fault diagnosis method and system |
CN114444382A (en) * | 2021-12-09 | 2022-05-06 | 中广核(北京)新能源科技有限公司 | Wind turbine generator gearbox fault diagnosis and analysis method based on machine learning algorithm |
-
2022
- 2022-10-21 CN CN202211290190.6A patent/CN115358281B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109657797A (en) * | 2018-12-24 | 2019-04-19 | 中国人民解放军32181部队 | Trouble diagnosibility analysis method based on hybrid diagnosis Bayesian network |
CN110411510A (en) * | 2019-07-18 | 2019-11-05 | 国家电网有限公司 | A kind of calculation method for excavating transformer station high-voltage side bus potentiality |
CN114496693A (en) * | 2020-11-11 | 2022-05-13 | 中微半导体设备(上海)股份有限公司 | Multi-zone heating device, lower electrode assembly, plasma processing device and temperature adjusting method |
CN113077172A (en) * | 2021-04-19 | 2021-07-06 | 瑞湖智科数据(苏州)有限公司 | Equipment state trend analysis and fault diagnosis method |
CN113505448A (en) * | 2021-06-09 | 2021-10-15 | 上海电力大学 | Wind turbine generator dynamic reliability evaluation method based on improved Bayesian network |
CN114237155A (en) * | 2022-02-24 | 2022-03-25 | 深圳市正和楚基科技有限公司 | Error prediction and compensation method, system and medium for multi-axis numerical control machining |
Non-Patent Citations (1)
Title |
---|
基于堆叠自编码网络的风电机组发电机状态监测与故障诊断;赵洪山等;《电力系统自动化》;20180424(第11期);全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN115358281A (en) | 2022-11-18 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN115358281B (en) | Machine learning-based cold and hot all-in-one machine monitoring control method and system | |
CN111275288B (en) | XGBoost-based multidimensional data anomaly detection method and device | |
CN106228270B (en) | Energy consumption prediction method and system for big data driven extrusion equipment | |
Michau et al. | Domain adaptation for one-class classification: monitoring the health of critical systems under limited information | |
CN110298552B (en) | Power distribution network individual power abnormality detection method combining historical electricity utilization characteristics | |
CN112947290B (en) | Edge cloud cooperation-based equipment state monitoring method and system and storage medium | |
Jiang et al. | Electrical-STGCN: An electrical spatio-temporal graph convolutional network for intelligent predictive maintenance | |
CN115358155A (en) | Power big data abnormity early warning method, device, equipment and readable storage medium | |
CN116700193A (en) | Factory workshop intelligent monitoring management system and method thereof | |
JP3718765B2 (en) | Plant diagnostic equipment | |
CN117272196A (en) | Industrial time sequence data anomaly detection method based on time-space diagram attention network | |
Levorato et al. | Fast anomaly detection in smartgrids via sparse approximation theory | |
CN117393076B (en) | Intelligent monitoring method and system for heat-resistant epoxy resin production process | |
CN114202179A (en) | Target enterprise identification method and device | |
CN117375237A (en) | Substation operation and maintenance method and system based on digital twin technology | |
CN117076258A (en) | Remote monitoring method and system based on Internet cloud | |
CN112580858A (en) | Equipment parameter prediction analysis method and system | |
CN117349583A (en) | Intelligent detection method and system for low-temperature liquid storage tank | |
Jiang et al. | A timeseries supervised learning framework for fault prediction in chiller systems | |
CN115424106A (en) | Trolley detection method and device, electronic equipment and storage medium | |
CN112988529A (en) | Method and system for predicting database system performance based on machine learning | |
CN117370824B (en) | Intelligent monitoring method and system for air inlet state of air compressor | |
CN117311295B (en) | Production quality improving method and system based on wireless network equipment | |
CN116760033B (en) | Real-time power demand prediction system based on artificial intelligence | |
CN117308275B (en) | Temperature difference-based pipeline connection abnormality detection method and 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 |