CN106971231B - Intelligent management expert system for grain storage environment of bulk grain transport vehicle - Google Patents
Intelligent management expert system for grain storage environment of bulk grain transport vehicle Download PDFInfo
- Publication number
- CN106971231B CN106971231B CN201710211400.0A CN201710211400A CN106971231B CN 106971231 B CN106971231 B CN 106971231B CN 201710211400 A CN201710211400 A CN 201710211400A CN 106971231 B CN106971231 B CN 106971231B
- Authority
- CN
- China
- Prior art keywords
- grain
- ventilation
- expert system
- rule
- base
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/02—Knowledge representation; Symbolic representation
- G06N5/022—Knowledge engineering; Knowledge acquisition
- G06N5/025—Extracting rules from data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/04—Inference or reasoning models
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/083—Shipping
- G06Q10/0832—Special goods or special handling procedures, e.g. handling of hazardous or fragile goods
Abstract
The invention discloses an intelligent management expert system for a grain storage environment of a bulk grain transport vehicle, which comprises an expert system database, a knowledge base, an inference machine, a man-machine interaction platform and a ventilation control execution mechanism. The inference machine selects rules in the rule base to compare and match one by one according to the grain condition report, and when the matched rules are not found, the inference machine infers a ventilation strategy according to a judgment algorithm meeting the mechanical ventilation standard of the grain industry, sends the ventilation strategy to the human-computer interaction platform, and then stores the grain condition report and the information of the unmatched rules into a fault table of the expert system database for perfecting the rules in the rule base. The knowledge base perfects a rule base model corresponding to different grain situations through a self-learning method; the knowledge base is also provided with a fact base besides the rule base, the grain condition reports and the ventilation strategies in each complete ventilation control process are stored in the fact base, and different grain condition reports and ventilation strategies can be generated into new rules for optimizing and perfecting the rule base.
Description
Technical Field
The invention belongs to an intelligent management expert system in the technical field of intelligent granaries, and particularly relates to an intelligent management expert system for a grain storage environment, which is suitable for a bulk grain transport vehicle.
Background
At present, along with the gradual establishment of main bulk grain logistics channels and bulk grain logistics nodes in China, the supply chain management of the links of bulk storage, bulk transportation, bulk loading, bulk unloading and whole circulation of the main transprovincial grain logistics channels and the formation of a modernized grain logistics system are basically realized, and the bulk grain transport vehicle is increasingly emphasized. The supply and demand of the food in China are extremely unbalanced, long-distance transprovincial and transregional grain transportation is often required, the duration is long, the quality of the food cannot be guaranteed due to the influence of weather damp and heat in the long-distance grain transportation process, and the food is mildewed and deteriorated occasionally. Therefore, the intelligent bulk grain transport vehicle capable of ensuring the safe storage in the grain circulation process is a necessary trend for the development of modern grain logistics.
Disclosure of Invention
In order to better guarantee the safety of grains in transportation, the invention provides an intelligent management expert system for the grain storage environment of a bulk grain transport vehicle.
In order to achieve the purpose, the invention adopts the following technical scheme: an intelligent management expert system for a grain storage environment of a bulk grain transport vehicle comprises an expert system database, a knowledge base, an inference machine, a man-machine interaction platform and a ventilation control execution mechanism; the man-machine interaction platform generates a grain condition report from the grain condition data acquired by the detection equipment in real time and records the grain condition report into an expert system database; the inference machine adopts a forward inference mechanism, judges a preliminary ventilation strategy according to the grain condition report, selects rules in a rule base of a knowledge base for comparison and matching, and corrects the preliminary ventilation strategy to obtain a final ventilation strategy aiming at the current grain condition; the man-machine interaction platform transmits the final ventilation strategy to a ventilation control execution mechanism for execution; wherein the content of the first and second substances,
the inference machine selects rules in the rule base to compare and match one by one according to the grain condition report, and when the matched rules are not found, the inference machine infers a ventilation strategy according to a judgment algorithm meeting the mechanical ventilation standard of the grain industry, sends the ventilation strategy to the human-computer interaction platform, and then stores the grain condition report and the information of the unmatched rules into a fault table of the expert system database for perfecting the rules in the rule base;
the knowledge base perfects a rule base model for dealing with different grain situations by a self-learning method according to the influence of the bulk grain transport vehicle on the grain quality in the grain transport process; the knowledge base is also provided with a fact base besides the rule base, the grain condition reports and the ventilation strategies in each complete ventilation control process are stored in the fact base, and different grain condition reports and ventilation strategies can be generated into new rules for optimizing and perfecting the rule base.
As a further improvement of the scheme, the formed rules of the complete ventilation process stored in the fact library at the initial stage of the establishment of the rule library by the knowledge base are directly used for expanding the rule library.
As a further improvement of the scheme, the functions of inquiring, modifying, adding and deleting the rules in the rule base are added to the human-computer interaction platform.
As a further improvement of the scheme, the human-computer interaction platform obtains grain condition data from the detection equipment in real time, obtains the average temperature, average moisture, temperature gradient and the average air temperature and humidity inside and outside the carriage of the grain, and calculates the relative air humidity RH under the grain bulk temperature by calling an expert system database to look up a table1And equilibrium relative humidity RH of the grain bulk2And generating a grain condition report and inputting the grain condition report into an expert system database.
As a further improvement of the scheme, when the intelligent management expert system for the grain storage environment of the bulk grain transport vehicle works, the man-machine interaction platform judges whether the current grain situation exceeds the standard or not, and if so, a grain situation exceeding alarm mechanism is started; the inference machine infers the obtained ventilation type, the estimated ventilation time and the current state of the current ventilation equipment, and determines whether ventilation is needed at present, whether ventilation is finished or not and whether current ventilation control is changed or not; when the inference machine judges that the ventilation target is finished, storing the ventilation mode, the ventilation time and the ventilation finishing effect of the ventilation process into a fact library list of a knowledge base; and finally, storing the determined ventilation control result in a rule base list, transmitting the rule base list to a man-machine interaction platform, and transmitting the rule base list to a ventilation control execution mechanism by the man-machine interaction platform for execution.
As a further improvement of the scheme, the maintenance work of the knowledge base inserts new rule entries by a manual input method on a human-computer interaction platform; deleting the rule items which are no longer needed in the rule base, or modifying and editing the data in the fact base to be used as new rules and adding the new rules into the rule base.
As a further improvement of the above scheme, when the inference engine is started, the grain condition report is read, a decision algorithm is used for preliminary decision, then a proper rule base entry is selected according to different grain types and regions, the rule object pointer starts to point to the first rule, and then according to the grain condition and the preliminary decision ventilation strategy, after the rule conditions are compared and matched one by one, the ventilation strategy of the rule matched with the current grain condition is finally obtained and used as a final inference conclusion; when the rule object pointer points to the last of the rule chain and no matching rule exists, the existing knowledge base of the system is indicated to be incapable of meeting the requirement of the user at this time, and the error related information of the rule which is not applicable at this time is stored in the fault table.
The invention discloses an intelligent management expert system for grain storage environment of a bulk grain transport vehicle, which is an intelligent management/control system developed for better guaranteeing the safety of grains in transportation, and the system is an intelligent management/control system integrating grain condition analysis, intelligent ventilation decision and ventilation control.
Drawings
Fig. 1 is a frame diagram of the intelligent management expert system for the grain storage environment of the bulk grain transport vehicle.
Fig. 2 is a main flow chart of the system grain storage environment management of the invention.
FIG. 3 is a system knowledge base maintenance workflow diagram of the present invention.
FIG. 4 is a flow diagram of the system inference engine operation of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Referring to fig. 1, the expert system for intelligent management of grain storage environment of bulk grain transport vehicle of the present invention mainly includes five parts: the system comprises an expert system database 1, a knowledge base 2, an inference machine 3, a man-machine interaction platform 4 and a ventilation control execution mechanism 5. The knowledge base 2 is mainly composed of two parts: rule base and fact base. The key point of the invention is how to adopt the current grain situation data to optimize and perfect the rules in the rule base, thereby being capable of controlling the grain situation more quickly and accurately according to the grain situation in the carriage and controlling the carriage of the bulk grain transport vehicle to keep a good grain storage environment.
According to the grain industry mechanical ventilation standard (grain industry standard L ST 1202-2002) and the influence of grain conditions such as grain temperature, grain moisture, air temperature and humidity inside and outside a carriage on grain quality, the expert system gradually establishes a set of rule base model and inference mechanism corresponding to different grain conditions through a self-learning method, establishes a grain storage environment optimization control expert system of the bulk grain transport vehicle, realizes prediction and expert ventilation control on the change of the grain storage environment in the carriage, and completes automatic regulation and control on the grain storage environment in the carriage.
The expert system database 1 is used for storing grain condition reports, grain condition data calculation table look-up, ventilation control strategies, control strategies required to be transmitted to the ventilation control execution mechanism 5 and the like transmitted by the man-machine interaction platform. The knowledge base comprises a rule base and an actual base, wherein the rule base is used for storing ventilation strategy judgment knowledge and regulation and control rules, the actual base is used for storing complete ventilation control process data and ventilation strategies of each round, and new rules can be generated and used for optimizing and perfecting the rule base. The inference machine 3 completes the derivation solving process of the knowledge by applying the rule knowledge in the knowledge base 2 according to the current data information; the human-computer interaction platform 4 is used for information interaction between the expert system and the user; and the ventilation control actuator 5 is used for an output actuator of the expert system control strategy.
The human-computer interaction platform 4 processes the grain condition data acquired from the detection equipment in real time, the average temperature, the average moisture, the temperature gradient, the average air temperature and humidity inside and outside the carriage and the like of the grain are obtained, and the RH is calculated by calling the expert system database 1 to look up a table1And RH2(RH1-relative humidity of the air at the grain bulk temperature; RH (relative humidity)2Equilibrium phase of the grain bulkTo humidity, RH1And RH2The method complies with the grain industry standard L ST1202-2002 mechanical ventilation technical regulation of grain storage), and then the grain situation report is generated and recorded into the expert system database 1.
The inference engine 3 adopts a forward inference mechanism to take out the grain condition report from the expert system database 1, and performs a preliminary judgment ventilation strategy according to a judgment algorithm following the standard, wherein the judgment algorithm is compiled according to the following table 1.
TABLE 1 reasoning machine 3 judgment algorithm basis (meeting grain industry standard L ST1202-2002 grain storage mechanical ventilation technical regulation)
Supplementary explanation: t is t1-outside air temperature; t is t2-the average temperature of the grain bulk; RH (relative humidity)1-relative humidity unit% of air at the grain bulk temperature; RH (relative humidity)2-equilibrium relative humidity unit% of the grain bulk.
And then, selecting rules in the rule base according to needs for further comparison and matching, finally reasoning out a ventilation strategy aiming at the current grain situation, sending the ventilation strategy to the human-computer interaction platform 4, and then transmitting the ventilation strategy to the ventilation control execution mechanism 5 by the human-computer interaction platform 4 for execution. In addition, each rule in the rule base consists of grain type and t2、t1、RH1、RH2Local safe moisture, ventilation strategy, ventilation estimated time and the like, and the inference machine 3 needs to compare and match the current grain situation data with rule conditions in a rule base to infer the ventilation strategy corresponding to the applicable rule.
The knowledge base 2 of the expert system is based on the influence of grain conditions such as grain temperature, grain moisture, air temperature and humidity inside and outside a carriage and the like on grain quality in the grain transportation process of the bulk grain transport vehicle, the expert system gradually establishes a set of rule base models corresponding to different grain conditions through a self-learning method, namely, a grain condition report and a ventilation strategy of each complete ventilation control process are stored in a fact base, and the grain types, t and the like contained in the complete ventilation control processes are stored in the fact base2、t1、RH1、RH2Data such as local safe moisture, ventilation strategy and ventilation estimated time can generate new rules for optimizing and perfecting the rule base.
The man-machine interaction platform 4 adds the function of inquiring, modifying, adding and deleting the rules in the rule base into the software, the knowledge base 2 of the expert system has the function of self-learning, the formed rules of the complete ventilation process stored in the fact base at the initial stage of establishing the rule base can be directly used for expanding the rule base, and the data in the fact base can be used for modifying and editing after the rule base is established and then is brought into the rule base; rules that are no longer applicable may also be deleted from the rule base to maintain the authenticity of the knowledge base.
When the inference machine 3 of the expert system operates, the rules in the rule base are selected to be compared and matched one by one, and the matched rules are not found, the ventilation strategy inferred according to the judgment algorithm is sent to the human-computer interaction platform, and then the grain condition report, the information of the unmatched rules and the like are stored in the fault table of the expert system database 1 and can be used for perfecting the rules in the rule base after the fault table is used.
The intelligent management expert system for the grain storage environment of the bulk grain transport vehicle establishes a rule base model and an inference mechanism for dealing with different grain situations in the grain transport process according to the influence of the grain situations such as grain temperature, grain moisture, air temperature and humidity inside and outside a carriage on the grain quality in the grain transport process, establishes an optimized control expert system for the grain storage environment of the bulk grain transport vehicle, realizes prediction and expert ventilation control on the change of the grain storage environment in the carriage, and completes automatic regulation and control on the grain storage environment in the carriage. The expert system related by the invention has a self-learning function, and can quickly and accurately control grain conditions according to the grain conditions in the carriage by virtue of the continuously optimized rule base model, so as to control the good grain storage environment in the carriage of the bulk grain transport vehicle.
The implementation of the invention is as follows.
1. Building a human-computer interaction platform 4 and a ventilation control actuating mechanism 5
Firstly, a human-computer interaction platform 4 is established, the subsequent whole expert system is established on the human-computer interaction platform 4 to operate, and the establishment of the human-computer interaction platform 4 is important because the interaction among all functional modules of the expert system is concerned. The execution unit, namely the ventilation control execution mechanism 5, is an output execution unit of an expert system control strategy and is also constructed firstly.
2. Establishing an expert System database 1
The expert system database 1 is used for storing grain condition data collected by the detection equipment, a grain condition report generated after the grain condition data is processed by the human-computer interaction platform 4, and RH1And RH2Calculating the table look-up, the rule items of the rule base, all the fact operation results of the fact base, the process data in the operation process of the expert system and the like. The expert system database 1 establishes that the grain condition data stored in the initial stage is from historical data obtained by experiments.
3. Preliminary set-up of inference engine 3 of expert system
The inference engine 3 of the expert system adopts a forward inference mechanism, and the inference algorithm of the inference engine 3 can be compiled according to the table 1 to carry out preliminary ventilation strategy judgment.
4. Preliminary set-up of expert system
Through the steps 1, 2 and 3, the expert system is initially established, and the whole system can be operated. The expert system infers a ventilation decision through an inference algorithm of the inference machine 3 which is preliminarily established according to grain situation experimental data stored in the expert system database 1, outputs the ventilation decision to the ventilation control execution mechanism 5 for execution, and can preliminarily realize the management control of the grain storage environment of the bulk grain vehicle.
6. Self-learning process of expert system
The grain condition report and the ventilation strategy of each complete ventilation control process are stored in a fact library, and the grain types, t, contained in the complete ventilation control processes2、t1、RH1、RH2Data such as local safe moisture, ventilation strategy, ventilation estimated time and the like can be converted into expert knowledge at the initial stage of establishment of an expert system and become rules in a rule base. The running process of the expert system is also a self-learning process, and in the running process, a fact libraryThe stored complete ventilation process data is continuously converted into rules of a rule base, the knowledge base of the expert system is continuously expanded, and the expert system is gradually improved.
5. Expert system control process
The human-computer interaction platform 4 reads grain condition data from the expert system database 1, obtains average temperature, average moisture, temperature gradient, average air temperature and humidity inside and outside a carriage and the like of grains, and calculates RH by looking up a table by using the expert system database 11And RH2And generating a grain condition report and inputting the grain condition report into an expert system database 1. And the inference machine 3 of the expert system adopts a forward inference mechanism to read the grain condition report from the expert system database 1, uses a preliminary judgment algorithm to carry out inference, then effectively selects rules in the rule base to carry out comparison and matching, infers a ventilation strategy aiming at the current grain condition and sends the ventilation strategy to the human-machine interaction platform 4. The man-machine interaction platform 4 judges whether the current grain situation exceeds the standard or not and whether a grain situation exceeding alarm mechanism needs to be started or not; according to the ventilation type, the estimated ventilation time and the current state of the current ventilation equipment obtained by inference, determining whether ventilation is needed currently, whether ventilation is finished, whether current ventilation control is changed, and the like; when the ventilation target is judged to be completed, the ventilation mode, the ventilation time and the ventilation completion effect of the ventilation process are stored in a fact base list of the knowledge base 2, the complete ventilation data stored in the fact base at the initial stage of the establishment of the rule base can be converted into rules for expanding the rule base, and the data in the fact base can be used for being modified and edited and then is included in the rule base after the establishment of the rule base; and finally, storing the determined ventilation control result in a rule base list of the knowledge base 2, transmitting the result to the man-machine interaction platform 4, and sending the result to the ventilation control execution mechanism 5. The above is the complete control process of the expert system.
The working of the invention will be described in accordance with the following description of fig. 2, 3 and 4:
FIG. 2 is a main flow chart of the work of the intelligent management expert system, as shown in the figure, the human-computer interaction platform 4 reads grain condition data from a database to obtain the average temperature, the average moisture and the temperature gradient of grains and the average air temperature inside and outside a carriageHumidity, etc., in calculating RH by calling an expert database to look up a table1And RH2And generating a grain condition report and inputting the grain condition report into an expert system database 1. The inference machine 3 of the expert system adopts a forward inference mechanism, effectively selects rules in a rule base according to a grain condition report and a judgment algorithm for comparison and matching, infers a ventilation strategy aiming at the current grain condition, sends the ventilation strategy to a human-computer interaction platform, judges whether the current grain condition exceeds the standard or not by the human-computer interaction platform, and starts a grain condition exceeding alarm mechanism if the current grain condition exceeds the standard; according to the ventilation type, the estimated ventilation time and the current state of the current ventilation equipment obtained by inference, determining whether ventilation is needed currently, whether ventilation is finished, whether current ventilation control is changed, and the like; when the ventilation target is judged to be completed, storing the ventilation mode, the ventilation time and the ventilation completion effect of the ventilation process into a fact library list; and finally, storing the determined ventilation control result in a rule base list, transmitting the result to the man-machine interaction platform 4, and sending the result to the ventilation control execution mechanism 5. The method comprises the following specific steps.
Step 101, start.
And 103, reading grain condition data from the database, and analyzing and processing the grain condition data.
And 105, operating a grain situation reasoning mechanism.
And step 108, storing the abnormal grain situation alarm information into a fact library list, and then executing step 107.
Step 109, obtaining the current ventilation type and ventilation time.
And step 110, updating the output results of the inferred ventilation mode, the operation of the ventilation equipment and the like into a rule base list, and then executing step 116 to finish.
And step 112, updating the rule base list according to the inferred information such as the ventilation mode, the ventilation equipment operation and the like.
Step 114, changing the control of the ventilation equipment and the information such as the estimated ventilation time, and then executing step 115.
And step 115, updating the inferred information such as the ventilation mode, the ventilation equipment operation and the like to a rule base list.
And step 116, ending.
FIG. 3 is a flow chart of the work flow of the intelligent management expert system knowledge base maintenance, as shown in the figure, the human-computer interaction platform 4 receives the maintenance instruction of the knowledge base 2 at the beginning of the main flow, and can enter the maintenance flow of the knowledge base 2, and the maintenance of the knowledge base 2 can insert a new rule entry through a method of manual input on the human-computer interaction platform 4; rule entries in the rule base that are no longer needed can be deleted; or modifying and editing the data in the fact base to be used as a new rule and adding the new rule into the rule base. The conversion from the fact base to the rule base is spontaneously carried out at the initial stage of establishing the rule base, and the self-learning and self-optimization of an expert system are realized. The method comprises the following specific steps.
In step 203, determine what is the knowledge base maintenance instruction received? If the conversion is between the fact base and the rule base, executing step 204; if the rule is added, step 205 is executed; if it is a delete rule, step 206 is performed.
Step 209 is selecting all rule instances to be added to the rule base on the human machine interface.
In step 211, determine if the addition is complete? If yes, go to step 214, otherwise go back to step 209.
At step 212, the entered rule entry is added to the rule base.
Step 206, all the rule list items needing to be deleted are selected on the human-computer interface, and then steps 207 and 208 are sequentially executed.
In step 214, determine if the repository maintenance operation is exited? If yes, go to step 215, otherwise go back to step 202.
And step 215, ending.
FIG. 4 is a flow chart of the inference engine of the intelligent management expert system, as shown in the figure, when the inference engine 3 is started, the grain condition report is read, the judgment algorithm is used for preliminary judgment, then appropriate rule base entries are selected according to different grain types and regions, the rule object pointer starts to point to a first rule, and then according to the grain condition and the preliminary judgment ventilation strategy, after rule conditions are compared and matched one by one, the ventilation strategy of the rule matched with the current grain condition is finally obtained to serve as a final inference conclusion; when the rule object pointer points to the last of the rule chain and no matching rule exists, the existing knowledge base of the system is indicated to be incapable of meeting the requirement of the user at this time, and the error related information of the rule which is not applicable at this time is stored in the fault table. The method comprises the following specific steps.
Step 302, reading the grain condition report, and performing preliminary reasoning according to a judgment algorithm.
In step 305, determine if all rules have been determined? If yes, go to step 308, otherwise go to step 307.
In step 308, determine if there is an applicable rule? If yes, go to step 309, otherwise go to steps 310 and 311 in turn.
And step 311, ending.
The flow analysis of the intelligent management expert system for the grain storage environment of the bulk grain transport vehicle and the introduction of the working process of the invention are described above. A large number of tests and experiments show that: by using the intelligent management expert system for the grain storage environment of the bulk grain transport vehicle, the reasoning judgment reliability and the strain capability of the system can be improved, and the intelligent level of ventilation decision can also be improved.
The foregoing is a detailed description of the present invention in connection with specific preferred embodiments and is not intended to limit the practice of the invention to those descriptions. For those skilled in the art to which the invention pertains, several simple deductions or substitutions, such as changes in the number of radiating elements and the form of the aperture, can be made without departing from the inventive concept, and should be considered as belonging to the scope of protection of the invention as determined by the claims submitted.
Claims (6)
1. An intelligent management expert system for a grain storage environment of a bulk grain transport vehicle comprises an expert system database (1), a knowledge base (2), an inference machine (3), a man-machine interaction platform (4) and a ventilation control execution mechanism (5); the man-machine interaction platform (4) generates a grain condition report from the grain condition data acquired from the detection equipment in real time and records the grain condition report into the expert system database (1); the inference machine (3) adopts a forward inference mechanism, judges a preliminary ventilation strategy according to the grain condition report, selects rules in a rule base of the knowledge base (2) for comparison and matching, and corrects the preliminary ventilation strategy to obtain a final ventilation strategy aiming at the current grain condition; the man-machine interaction platform (4) transmits the final ventilation strategy to a ventilation control execution mechanism (5) for execution; the method is characterized in that:
the inference machine (3) selects rules in the rule base to compare and match one by one according to the grain condition report, and when no matched rule is found, the inference machine infers a ventilation strategy according to a judgment algorithm meeting the mechanical ventilation standard of the grain industry and sends the ventilation strategy to the human-computer interaction platform (4), and then the grain condition report and the information of the unmatched rule are stored in a fault table of the expert system database (1) to perfect the rules in the rule base;
the knowledge base (2) perfects a rule base model for different grain conditions by a self-learning method according to the influence of the bulk grain transport vehicle on the grain quality in the grain transport process: the knowledge base (2) is also provided with a fact base besides the rule base, the grain condition reports and the ventilation strategies in each complete ventilation control process are stored in the fact base, and different grain condition reports and ventilation strategies can be generated into new rules for optimizing and perfecting the rule base;
the working process of the intelligent management expert system is as follows:
1. build a man-machine interaction platform (4) and a ventilation control execution mechanism (5)
2. Establishing expert system database (1)
The expert system database (1) is used for storing grain condition data collected by the detection equipment, a grain condition report generated after the grain condition data is processed by the human-computer interaction platform (4), and RH1And RH2Calculating table look-up, rule items of a rule base, all fact operation results of a fact base and process data in the operation process of the expert system, wherein: RH (relative humidity)1-relative humidity unit% of air at the grain bulk temperature; RH (relative humidity)2Equilibrium relative humidity unit% of the grain heapThe database (1) establishes that the grain condition data stored in the initial stage is from historical data obtained by experiments;
3. preliminary set-up of an inference engine (3) of an expert system
An inference machine (3) of the expert system adopts a forward inference mechanism to compile an inference algorithm of the inference machine (3) to carry out preliminary ventilation strategy judgment;
4. preliminary set-up of expert system
Through the steps 1, 2 and 3, an expert system is preliminarily established, the whole system can be operated, the expert system infers a ventilation decision through an inference algorithm of an inference machine (3) preliminarily established according to grain situation experiment data stored in an expert system database (1), and outputs the ventilation decision to a ventilation control executing mechanism (5) for execution, and the management control of the grain storage environment of the bulk grain vehicle is preliminarily realized;
5. self-learning process of expert system
The grain condition report and the ventilation strategy of each complete ventilation control process are stored in a fact library, and the grain types, t, contained in the complete ventilation control processes2、t1、RH1、RH2Local safe moisture, ventilation strategy and ventilation estimated time data are converted into expert knowledge at the initial stage of establishing an expert system and become rules in a rule base, wherein t1-outside air temperature; t is t2-average temperature of the grain heap, the running process of the expert system is also a self-learning process, during the running process, the complete ventilation process data stored in the fact base is continuously converted into rules of the rule base, the knowledge base of the expert system is continuously expanded, and the expert system is gradually improved;
6. expert system control process
The human-computer interaction platform (4) reads grain condition data from the expert system database (1), calculates average temperature, average moisture, temperature gradient of grains and average air temperature and humidity inside and outside a carriage, and calculates RH by looking up a table through the expert system database (1)1And RH2The grain information report is generated and recorded into an expert system database (1), and a reasoning machine (3) of the expert system reads the grain information from the expert system database (1) by adopting a forward reasoning mechanismInforming that a preliminary judgment algorithm is used for reasoning, then rules in a rule base are effectively selected for comparison and matching, a ventilation strategy aiming at the current grain situation is deduced and sent to a human-computer interaction platform (4), the human-computer interaction platform (4) judges whether the current grain situation exceeds the standard or not, and whether a grain situation exceeding alarm mechanism needs to be started or not; according to the ventilation type obtained by inference, the estimated ventilation time and the current state of the current ventilation equipment, determining whether ventilation is needed currently, whether ventilation is finished or not, and whether current ventilation control is changed or not; and when the ventilation target is judged to be completed, storing the ventilation mode, the ventilation time and the ventilation completion effect of the starting ventilation process into a fact library list of the knowledge base (2), and finally storing the determined ventilation control result into a rule library list of the knowledge base (2), transmitting the determined ventilation control result to the man-machine interaction platform (4) and transmitting the ventilation control result to the ventilation control execution mechanism (5).
2. The bulk grain transport vehicle grain storage environment intelligent management expert system of claim 1, characterized in that: the rules formed by the complete ventilation process stored in the initial situation library established by the knowledge base (2) are directly used for expanding the rule base.
3. The bulk grain transport vehicle grain storage environment intelligent management expert system of claim 1, characterized in that: the man-machine interaction platform (4) is added with the functions of inquiring, modifying, adding and deleting the rules in the rule base.
4. The bulk grain transport vehicle grain storage environment intelligent management expert system of claim 1, characterized in that: the man-machine interaction platform (4) obtains grain condition data from the detection equipment in real time, obtains the average temperature, average moisture, temperature gradient of the grain and the average air temperature and humidity inside and outside the carriage, and calculates the relative air humidity RH at the grain bulk temperature by calling the expert system database (1) to look up a table1And equilibrium relative humidity RH of the grain bulk2And generating a grain condition report and inputting the grain condition report into an expert system database (1).
5. The bulk grain transport vehicle grain storage environment intelligent management expert system of claim 4, characterized in that: the maintenance work of the knowledge base (2) inserts new rule items through a manual input method on a man-machine interaction platform (4); deleting the rule items which are no longer needed in the rule base, or modifying and editing the data in the fact base to be used as new rules and adding the new rules into the rule base.
6. The bulk grain transport vehicle grain storage environment intelligent management expert system of claim 1, characterized in that: when the inference machine (3) is started, the grain condition report is read, a judgment algorithm is used for preliminary judgment, then a proper rule base entry is selected according to different grain types and regions, a rule object pointer points to a first rule, and then according to the grain condition and a preliminary judgment ventilation strategy, after rule conditions are compared and matched one by one, a ventilation strategy of the rule matched with the current grain condition is finally obtained and used as a final inference conclusion; when the rule object pointer points to the last of the rule chain and no matching rule exists, the existing knowledge base of the system is indicated to be incapable of meeting the requirement of the user at this time, and the error related information of the rule which is not applicable at this time is stored in the fault table.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710211400.0A CN106971231B (en) | 2017-03-31 | 2017-03-31 | Intelligent management expert system for grain storage environment of bulk grain transport vehicle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710211400.0A CN106971231B (en) | 2017-03-31 | 2017-03-31 | Intelligent management expert system for grain storage environment of bulk grain transport vehicle |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106971231A CN106971231A (en) | 2017-07-21 |
| CN106971231B true CN106971231B (en) | 2020-08-04 |
Family
ID=59337300
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710211400.0A Active CN106971231B (en) | 2017-03-31 | 2017-03-31 | Intelligent management expert system for grain storage environment of bulk grain transport vehicle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106971231B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109405192B (en) * | 2018-10-23 | 2020-10-23 | 苏州安省建筑设计有限公司 | Indoor ventilation method, equipment, server terminal and system |
| CN110083586B (en) * | 2019-03-21 | 2022-04-08 | 大连海事大学 | Energy pile knowledge base system assisting energy pile design and construction method thereof |
| CN111191983A (en) * | 2019-12-25 | 2020-05-22 | 航天信息股份有限公司 | Method and system for providing guidance information for intelligent grain storage |
| CN114263488A (en) * | 2021-12-24 | 2022-04-01 | 四川省交通勘察设计研究院有限公司 | Highway tunnel ventilation control method and system based on external environment self-learning |
| CN115454162B (en) * | 2022-08-31 | 2024-01-30 | 浪潮通用软件有限公司 | Intelligent temperature control method, equipment and medium for grain storage |
| CN115936122B (en) * | 2023-03-13 | 2023-05-23 | 南京感动科技有限公司 | Method for processing alarm data by rule engine based on expert system |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR0169808B1 (en) * | 1995-03-29 | 1999-01-15 | 경주현 | Fault diagonistic expert system and diagonistic method |
| CN101710393A (en) * | 2009-11-25 | 2010-05-19 | 北京航空航天大学 | Method for knowledge expressing and reasoning mechanism of expert system |
| CN101093559B (en) * | 2007-06-12 | 2010-06-23 | 北京科技大学 | Method for constructing expert system based on knowledge discovery |
| CN105260778A (en) * | 2015-11-05 | 2016-01-20 | 国家电网公司 | Power transformer fault diagnosis system based on expert database |
| CN105929873A (en) * | 2016-04-15 | 2016-09-07 | 中国电子科技集团公司第三十八研究所 | Intelligent bulk grain transport vehicle system with function of bulk grain online management |
-
2017
- 2017-03-31 CN CN201710211400.0A patent/CN106971231B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR0169808B1 (en) * | 1995-03-29 | 1999-01-15 | 경주현 | Fault diagonistic expert system and diagonistic method |
| CN101093559B (en) * | 2007-06-12 | 2010-06-23 | 北京科技大学 | Method for constructing expert system based on knowledge discovery |
| CN101710393A (en) * | 2009-11-25 | 2010-05-19 | 北京航空航天大学 | Method for knowledge expressing and reasoning mechanism of expert system |
| CN105260778A (en) * | 2015-11-05 | 2016-01-20 | 国家电网公司 | Power transformer fault diagnosis system based on expert database |
| CN105929873A (en) * | 2016-04-15 | 2016-09-07 | 中国电子科技集团公司第三十八研究所 | Intelligent bulk grain transport vehicle system with function of bulk grain online management |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106971231A (en) | 2017-07-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106971231B (en) | Intelligent management expert system for grain storage environment of bulk grain transport vehicle | |
| CN110493025B (en) | Fault root cause diagnosis method and device based on multilayer digraphs | |
| CN107864174A (en) | A kind of rule-based internet of things equipment interlock method | |
| KR102229859B1 (en) | Operation management method, apparatus and system using machine learning and transfer learning | |
| CN112422699A (en) | Unmanned aerial vehicle cluster action scheme generation method based on dynamic adjustment | |
| CN115033724B (en) | Multi-mode modulation algorithm-based method for identifying abnormal working conditions of electric smelting magnesium furnace | |
| CN115167562A (en) | Method and device for controlling temperature of machine room | |
| CN115081119A (en) | Method, device and equipment for optimizing train loading and readable storage medium | |
| Bunin et al. | Input filter design for feasibility in constraint-adaptation schemes | |
| US20230022505A1 (en) | Control system | |
| CN116414094A (en) | Intelligent scheduling method and system for welding assembly | |
| CN103714262B (en) | A kind of thermal technology's soft-sensing model update method based on buffer stopper timing Design | |
| CN116430805A (en) | Workshop scheduling control method and device, production line and working machine | |
| Braun et al. | Continuous Integration of Optimal Control Based Flight Control Law Clearance | |
| CN113687651B (en) | Path planning method and device for dispatching vehicles on demand | |
| US11629856B2 (en) | Apparatus for managing combustion optimization and method therefor | |
| JP6457467B2 (en) | Ladder program management device | |
| CN106990750B (en) | Ladder diagram online editing method | |
| CN105740822A (en) | Mechanical fault diagnosis optimization method and system | |
| CN113507125A (en) | Adaptive load transfer method, system and medium for active power distribution network | |
| CN117474441B (en) | Unmanned warehouse access path management method based on intelligent logistics big data | |
| CN116384715B (en) | Robot operation and maintenance management method of digital robot industrial chain | |
| CN116521278A (en) | Reactive scheduling method, device, system and medium | |
| CN115358630A (en) | Space mission control method and system based on intelligent closed-loop control | |
| CN117808250A (en) | Beat design method, device, equipment and medium of equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 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 |