CN-121979345-A - Intelligent storage internet of things monitoring and control system for tobacco production

Abstract

The invention discloses an intelligent storage Internet of things monitoring and controlling system for tobacco production, which comprises the following steps of constructing continuous monitoring data by collecting temperature, humidity, gas components and inventory identification information in storage environment at multiple points, comprehensively estimating the storage environment and inventory state by adopting an improved horizon estimation method on the basis of the continuous monitoring data to obtain a result reflecting state change, constructing a control barrier function based on the estimation result and used for forming a safety constraint dynamically adjusted along with the state change, generating an environment regulation and control instruction under the limitation of the safety constraint, executing regulation and control operation through equipment such as ventilation, dehumidification, humidification and gas emission, acquiring the running state of executing equipment and feeding back updated monitoring data to form an automatic closed-loop control process, and realizing continuous monitoring and safe and stable automatic regulation and control of the tobacco storage environment. The invention belongs to the technical field of industrial automatic control and Internet of things.

Inventors

• WANG ZENGLI
• Wen Yongyan
• XU YONG

Assignees

• 山东恒麟智能科技有限公司

Dates

Publication Date

20260505

Application Date

20260209

Claims (8)

1. 1. Intelligent storage thing networking monitoring and control system towards tobacco production, its characterized in that includes following module: the multi-source sensing module is used for collecting multi-position temperature, relative humidity, gas component concentration and inventory carrier identification information in the storage space, adding corresponding collecting time and collecting position for the collected data and generating original observation data; the association construction module is used for grouping and aligning the original observation data with a time sequence based on the acquisition position and the inventory carrier information to generate a continuous observation sequence; The horizon estimation module is used for constructing a state estimation problem by taking a continuous observation sequence as input in a sliding time window, and executing improved horizon estimation based on evolution constraint among the continuous observation sequences to generate a state track and a consistency index; The control barrier function construction module is used for constructing a control barrier function set based on the state track, updating the control barrier function set according to the state track and the consistency index, and generating a dynamic safety constraint model; The constraint control module receives the state track and the dynamic safety constraint model and generates an environment regulation instruction in a feasible control domain defined by a control barrier function set; the execution mechanism module receives the environment regulation instruction and executes corresponding ventilation, dehumidification, humidification and gas discharge actions; and the closed loop feedback module is used for collecting the running state of the execution mechanism module to form feedback data and transmitting the feedback data back to the association construction module, updating the continuous observation sequence and outputting the storage environment regulation and control result meeting the dynamic safety constraint model.
2. 2. The intelligent warehouse internet of things monitoring and control system for tobacco production of claim 1, wherein the multi-source sensing module comprises: The temperature and humidity acquisition unit is used for respectively acquiring environmental temperature data and relative humidity data at a plurality of different physical positions in the storage space, wherein the multi-position temperature is a real-time environmental temperature value corresponding to the acquisition position, and the relative humidity is a real-time environmental relative humidity value corresponding to the acquisition position; a gas component collection unit that collects gas component concentration data at the plurality of collection locations, the gas component concentration data including an oxygen concentration and a carbon dioxide concentration reflecting a warehouse environment state; an inventory carrier acquisition unit for reading inventory carrier identification information on an inventory carrier, the inventory carrier identification information including a unique identification code for distinguishing the inventory carrier and a batch identification for distinguishing a tobacco source; The acquisition data combination unit combines the temperature data, the relative humidity data and the gas component concentration data acquired at the same acquisition position with the corresponding read inventory carrier identification information to form acquisition data in the same acquisition period; An adding unit for adding the acquisition time to the acquired data by a unified time reference; And the result output unit is used for attaching the acquisition position corresponding to the acquisition data with the attached acquisition time as an acquisition position identifier to form original observation data containing acquisition contents, acquisition time and acquisition position.
3. 3. The intelligent storage internet of things monitoring and controlling system for tobacco production according to claim 1, wherein the association construction module comprises receiving original observation data, extracting acquisition positions, carrier storage identification information and acquisition time, grouping the original observation data by taking a combination of the acquisition positions and the carrier storage identification information as a grouping key to generate original observation data subsets, arranging the original observation data according to the sequence of the acquisition time in each original observation data subset to form an original observation data sequence, carrying out time sequence alignment processing on the original observation data sequence according to the sampling period based on a preset unified sampling period, selecting one of the original observation data sequences as aligned data of the sampling period when a plurality of the original observation data exist in the same sampling period, generating complementary data according to the original observation data in adjacent sampling periods when the original observation data do not exist in a certain sampling period, and sequentially connecting the data subjected to grouping, sequencing and time sequence alignment processing according to the sampling period to generate a continuous observation sequence.
4. 4. The intelligent warehouse internet of things monitoring and control system for tobacco production of claim 1, wherein the horizon estimation module comprises: the sequence receiving unit is used for receiving the continuous observation sequence output by the association construction module; The change evaluation unit is used for calculating the change degree of the original observation data corresponding to the adjacent acquisition time based on the continuous observation sequence and generating a change evaluation result; the self-adaptive horizon generating unit is used for screening original observation data from the continuous observation sequence according to the change evaluation result, correcting the screening result by combining the consistency index output in the last evaluation period, and generating a self-adaptive horizon observation set; the window determining unit is used for determining a sliding time window according to the time distribution range of the self-adaptive horizon observation set, and forming state estimation input by the self-adaptive horizon observation set covered by the sliding time window; The state variable sequence construction unit is used for defining state variables for each sampling time in the sliding time window and forming a state variable sequence; The constraint construction unit is used for constructing state evolution constraints between adjacent state variables based on the state variable sequences and constructing observation consistency constraints between the state variables and the self-adaptive horizon observation set based on state estimation input; The prior introducing unit is used for introducing the state estimation result output by the tail end of the last sliding time window into prior state constraint, and acting on the state variable sequence together with state evolution constraint and observation consistency constraint; The optimization solving unit is used for constructing a state estimation optimizing problem based on the state variable sequence, the state evolution constraint, the observation consistency constraint and the prior state constraint and solving the state estimation optimizing problem, and generating a state estimation result in the sliding time window and forming a state track; The track consistency assessment unit is used for generating a track consistency result based on the state track; and the tail end correction and output unit is used for carrying out constraint correction on the state estimation result corresponding to the tail end of the state track according to the track consistency result, outputting the corrected state estimation result and generating a consistency index based on the track consistency result.
5. 5. The intelligent warehouse internet of things monitoring and control system for tobacco production of claim 1, wherein the control barrier function construction module comprises: the input receiving unit is used for receiving the state track and the consistency index corresponding to the state track; The constraint quantity construction unit is used for constructing constraint quantity used for representing the relative safety requirement of the state variable based on the state variable corresponding to each sampling moment in the state track; A barrier function construction unit, configured to construct a control barrier function by using the constraint quantity as an input, and form a control barrier function set by combining control barrier functions constructed for different constraint quantities; A constraint model generation unit for generating a dynamic security constraint model for constraining the control variables based on the control barrier function set; The updating judging unit is used for judging the adaptation condition of the current state track relative to the control barrier function set based on the consistency index, and generating an updating judging result when the adaptation condition changes; And the online updating unit is used for updating the control barrier function set by taking the latest state track as input after the updating judgment result is generated, wherein the updating comprises the steps of recalculating the constraint quantity corresponding to each control barrier function in the control barrier function set, reconstructing the control barrier function set based on the recalculated constraint quantity, updating the dynamic safety constraint model and outputting the dynamic safety constraint model.
6. 6. The intelligent warehouse internet of things monitoring and control system for tobacco production of claim 1, wherein the constraint control module comprises: The input receiving unit is used for receiving the state track and the dynamic safety constraint model; A control variable definition unit configured to define a control variable set including a ventilation control amount, a dehumidification control amount, a humidification control amount, and a gas discharge control amount; The feasible control domain construction unit is used for taking the dynamic safety constraint model as constraint input, using the control barrier function set in the dynamic safety constraint model as a control variable set, generating a control variable feasible value range meeting the constraint condition of the control barrier function set, and determining the control variable feasible value range as a feasible control domain; The candidate control input generation unit is used for generating a candidate control variable value set by taking the end state of the state track as input, and providing the candidate control variable value set for the feasible control domain construction unit to carry out constraint judgment; The constraint judging unit is used for carrying out matching judgment on the candidate control variable value set and the feasible control domain, reserving the candidate control variable value falling into the feasible control domain and generating a feasible candidate control variable set; the target control variable selection unit is used for selecting a target control variable value from the feasible candidate control variable set; And the instruction generation unit is used for generating an environment regulation instruction according to the target control variable value.
7. 7. The intelligent warehouse internet of things monitoring and control system for tobacco production of claim 1, wherein the actuator module comprises: The instruction receiving unit is used for receiving the environment regulation and control instruction and analyzing the environment regulation and control instruction to generate ventilation control quantity, dehumidification control quantity, humidification control quantity and gas emission control quantity; the control quantity analysis unit is used for extracting target parameters corresponding to the ventilation control quantity, the dehumidification control quantity, the humidification control quantity and the gas emission control quantity from the environment regulation and control instruction and respectively associating the target parameters to corresponding execution mechanisms; the ventilation execution unit is used for driving the ventilation equipment to execute start and stop or adjust the operation intensity according to the ventilation control quantity so as to complete ventilation action; the dehumidification execution unit is used for driving the dehumidification equipment to execute start-stop or adjust the operation intensity according to the dehumidification control quantity so as to complete the dehumidification action; the humidifying executing unit is used for driving the humidifying equipment to execute start and stop or regulate humidifying output according to the humidifying control quantity so as to complete humidifying action; And the gas discharge execution unit is used for driving the gas discharge device to execute start and stop or adjust the discharge intensity according to the gas discharge control quantity so as to complete the gas discharge action.
8. 8. The intelligent warehouse internet of things monitoring and control system for tobacco production of claim 1, wherein the closed loop feedback module comprises: The state acquisition unit is used for acquiring the running state of the execution mechanism module, respectively acquiring the start-stop state and the running strength parameter of the ventilation execution unit, the start-stop state and the running strength parameter of the dehumidification execution unit, the start-stop state and the humidification output parameter of the humidification execution unit, and the start-stop state and the emission strength parameter of the gas emission execution unit, and generating the running state data of the execution mechanism; the marking unit is used for adding feedback time to the running state data of the executing mechanism and adding an acquisition position corresponding to the running state data of the executing mechanism; The feedback unit is used for transmitting the operating state data of the executing mechanism of the additional feedback moment and the acquisition position back to the association construction module; The sequence positioning unit is used for determining a continuous observation sequence corresponding to the running state data of the execution mechanism according to the acquisition position and determining a corresponding sampling period of the running state data of the execution mechanism in the continuous observation sequence according to the feedback moment; And the sequence updating unit is used for writing the running state data of the executing mechanism into the continuous observation sequence corresponding to the sampling period to form a continuous observation sequence containing the original observation data and the running state data of the executing mechanism, and outputting a storage environment regulation and control result meeting the dynamic safety constraint model based on the continuous observation sequence containing the original observation data and the running state data of the executing mechanism.

Description

Intelligent storage internet of things monitoring and control system for tobacco production Technical Field The invention relates to the technical field of industrial automatic control and Internet of things, in particular to an intelligent storage Internet of things monitoring and controlling system for tobacco production. Background Along with the development of the tobacco production process to informatization and automation, the requirements of the tobacco storage link on the fine management and control of environmental conditions and inventory states are continuously improved. At present, tobacco storage is generally monitored through arranging a temperature and humidity sensor, a gas detection device and a manual inspection mode in the storage, and ventilation, dehumidification, humidification and other devices are controlled according to an empirical threshold or a fixed rule so as to maintain the storage quality of tobacco. The existing tobacco warehouse monitoring and control technology still has obvious defects. On one hand, the existing system relies on single-point or small quantity of sensing data to perform environment judgment, lacks comprehensive utilization of multi-position and multi-time scale information, is difficult to timely and accurately reflect integral changes of storage environment and stock state, and is easy to cause state perception lag or judgment deviation. On the other hand, the existing control mode is generally triggered by a static threshold value or a simple rule, lacks the prediction capability of environmental state evolution trend, is mainly fixedly set in control constraint, cannot be dynamically adjusted along with storage state change, and is easy to cause excessive regulation or delayed response, so that tobacco quality risk is increased. In addition, the relevance among monitoring, decision making and execution in the existing system is weak, the running state of the execution equipment is difficult to timely feed back and participate in subsequent control decisions, and a stable and reliable closed-loop automatic control mechanism is difficult to form. Therefore, how to provide an intelligent storage internet of things monitoring and control system for tobacco production is a problem that needs to be solved by those skilled in the art. Disclosure of Invention The invention aims to provide an intelligent storage internet of things monitoring and controlling system for tobacco production, which continuously estimates storage states by fusing multi-source environment and storage monitoring data, generates environment regulation and control instructions under a safety constraint condition, realizes automatic control of ventilation, dehumidification, humidification and gas emission, and has the advantages of timely monitoring, forward looking control and stable operation. According to the embodiment of the invention, the intelligent storage internet of things monitoring and controlling system for tobacco production comprises the following steps: the multi-source sensing module is used for collecting multi-position temperature, relative humidity, gas component concentration and inventory carrier identification information in the storage space, adding corresponding collecting time and collecting position for the collected data and generating original observation data; the association construction module is used for grouping and aligning the original observation data with a time sequence based on the acquisition position and the inventory carrier information to generate a continuous observation sequence; The horizon estimation module is used for constructing a state estimation problem by taking a continuous observation sequence as input in a sliding time window, and executing improved horizon estimation based on evolution constraint among the continuous observation sequences to generate a state track and a consistency index; The control barrier function construction module is used for constructing a control barrier function set based on the state track, updating the control barrier function set according to the state track and the consistency index, and generating a dynamic safety constraint model; The constraint control module receives the state track and the dynamic safety constraint model and generates an environment regulation instruction in a feasible control domain defined by a control barrier function set; the execution mechanism module receives the environment regulation instruction and executes corresponding ventilation, dehumidification, humidification and gas discharge actions; and the closed loop feedback module is used for collecting the running state of the execution mechanism module to form feedback data and transmitting the feedback data back to the association construction module, updating the continuous observation sequence and outputting the storage environment regulation and control result meeting the dynamic safety constraint model. Optionally, the