An information-based concrete mixing station management system

Abstract

The present invention relates to the field of information management technology, and specifically to an information-based concrete mixing station management system. In the present invention, by periodically allocating status labels of concrete material inventory balances and generating time series, a dynamic label mapping relationship can be established for the inventory management of concrete materials, thereby enhancing the coupling between inventory status and consumption trends. In the process of using the state label sequence to deduce the future state change path, the frequency statistics and transition probability modeling between label pairs are adopted to enable the inventory change trend prediction to have data-driven evolution capabilities, thereby improving the adaptability and foresight of the prediction. In terms of conveyor belt operation status analysis, with the help of the normalized vector form of the operating parameters tension, belt speed and motor load, the operation trajectory of continuous time periods is generated in the potential energy space, so that the operation status can be concretely expressed in the multi-dimensional space and the jamming trend can be monitored, thereby enhancing the accuracy of abnormal state identification.

Description

Technical Field

[0001] The present invention relates to the technical field of information management, and in particular to an information-based concrete mixing station management system. Background Art

[0002] The information-based concrete mixing plant management system uses information technology to comprehensively manage and control the concrete mixing plant, primarily covering production scheduling, equipment monitoring, data collection and processing, and other aspects of the concrete mixing plant. Through automation, it enables real-time monitoring of the operating status of mixing plant equipment, automatic scheduling of production plans, management of concrete materials, and control of batching accuracy.

[0003] The existing information-based management system for concrete mixing plants mainly relies on static monitoring of production scheduling and equipment status. It can only perform general scheduling based on the current inventory level, making it difficult to predict the upcoming risk of material shortages. In the operation monitoring of conveyor belts, only threshold triggers can be used to determine whether there are operational anomalies, ignoring the operating trends and change trajectories within continuous time periods, which can easily cause delayed identification of blocking trends. In terms of identifying the blockage status at the feed inlet, it usually relies on sensor data at a single point in time. It is difficult to determine whether the blockage status is sporadic or a continuous abnormality, and it is prone to misjudgment or response delays. For example, in a high-intensity production stage, if the blockage is judged only based on the increase in motor load at a certain point in time, short-term fluctuations will be misjudged as abnormalities, causing unnecessary equipment shutdowns and scheduling errors, limiting the intelligence level and preventive maintenance capabilities of the management system. Summary of the Invention

[0004] The purpose of the present invention is to solve the shortcomings of the prior art and to propose an information-based concrete mixing station management system.

[0005] In order to achieve the above-mentioned purpose, the present invention adopts the following technical solutions: an information-based concrete mixing station management system includes:

[0006] The inventory status recognition module obtains the total daily concrete material consumption of the concrete mixing station and calculates the corresponding concrete material inventory balance. It assigns status labels to the concrete material inventory balances according to fixed time periods to obtain a status label sequence.

[0007] The state transition deduction module extracts state label pairs of adjacent time periods in the state label sequence, predicts the future change path of the concrete material inventory balance, and obtains the inventory change prediction result;

[0008] The operation potential energy mapping module obtains the operating parameters of the mixing station conveyor belt and performs normalization processing, maps them to the potential energy space in chronological order, and constructs the conveyor belt potential energy distribution map;

[0009] The potential energy trend identification module divides the potential energy distribution map of the conveyor belt into multiple local neighborhoods, calculates the local potential energy density within the local neighborhood to identify the operating status of the conveyor belt, and adjusts the operating mode of the conveyor belt based on the inventory change prediction results to obtain the conveyor belt control results;

[0010] The Boolean sequence construction module collects the opening and closing signals of the mixing station feed port in real time based on the conveyor belt control results after the conveyor belt is adjusted, and constructs the Boolean state sequence during the feed port operation;

[0011] The feed inlet abnormality analysis module compares the Boolean state sequences of the history and the current operation stage based on the collected opening and closing signals, determines the different blockage states of the feed inlet, and generates a feed inlet blockage state warning signal.

[0012] As a further solution of the present invention, the step of obtaining the state tag sequence is specifically as follows:

[0013] Obtain the total daily concrete material consumption of the concrete mixing station, calculate the corresponding concrete material consumption in each time period according to a fixed time cycle, and compare it with the concrete material inventory balance of the mixing station in the corresponding time period to obtain the comparison results of concrete material consumption and balance;

[0014] Different concrete material inventory balance status labels are assigned to the concrete material consumption and balance comparison results in each time period. The status labels include sufficient, critical, and shortage. All status labels are integrated to obtain a status label sequence.

[0015] As a further solution of the present invention, the steps for obtaining the inventory change forecast result are specifically as follows:

[0016] Extracting state tag pairs of adjacent time periods in the state tag sequence, comparing the state tag contents of the state tag pairs of adjacent time periods, determining whether the state has changed, counting the transition frequencies of each state change in all time periods, and constructing a state tag transition frequency table;

[0017] Initializing a Markov chain model, inputting the state label transfer frequency table into the Markov chain model, and constructing a corresponding state label transfer probability matrix to predict the transfer probability of the state label of the current concrete material inventory balance to the state labels of other concrete material inventory balances in multiple future time periods, thereby obtaining a future transfer probability prediction result;

[0018] According to the future transfer probability prediction result, a future change path of the concrete material inventory balance is identified. The future change path includes a continuous shortage of the concrete material inventory balance, a rebound to a critical state, and a gradual recovery to a sufficient state, thereby obtaining an inventory change prediction result.

[0019] As a further solution of the present invention, the steps for obtaining the potential energy distribution diagram of the conveyor belt are specifically as follows:

[0020] Obtaining and normalizing the conveyor belt operating parameters of the mixing station, wherein the conveyor belt operating parameters include the conveyor belt tension, belt speed, and motor load, and obtaining the processed conveyor belt operating parameters;

[0021] The processed conveyor belt operating parameters of each time period are respectively combined into corresponding vector forms and mapped to the potential energy space in chronological order. In the potential energy space, the conveyor belt operating parameters represent the conveyor belt operating status points in each time period, and a conveyor belt potential energy distribution diagram is constructed.

[0022] As a further solution of the present invention, the steps for obtaining the conveyor belt control result are specifically as follows:

[0023] Based on the conveyor belt potential energy distribution map, the conveyor belt running state point is divided into multiple local neighborhoods according to the distance in the potential energy space according to the comparison result, and the local neighborhood division result is obtained;

[0024] Based on the local neighborhood division results, the local potential energy density of each conveyor belt operation status point in its corresponding local neighborhood is calculated, the aggregation degree and density gradient change of each conveyor belt operation status point are analyzed according to the local potential energy density, and the corresponding density area boundaries are divided;

[0025] Obtain the position of the conveyor belt operating parameters in the potential energy space, calculate the spatial position offset between consecutive time periods, determine the offset trajectory based on the spatial position offset, compare the offset trajectory with the density area boundary, and use the comparison result to identify whether the conveyor belt operating status is migrating towards a blocking trend, thereby obtaining the conveyor belt operating status analysis result;

[0026] Combined with the conveyor belt operation status analysis result and the future change path of the concrete material inventory balance in the inventory change prediction result, the conveyor belt operation mode is adjusted with reference to the conveyor belt operation status and the future inventory balance to obtain the conveyor belt control result.

[0027] As a further solution of the present invention, the step of obtaining the Boolean state sequence is specifically as follows:

[0028] Based on the conveyor belt control result, the opening and closing signals of the mixing station feed port after the conveyor belt is adjusted are collected in real time, and the opening and closing signals are counted according to the number of switching of the opening and closing actions within a specified time. By setting an opening and closing frequency threshold, the time period in which the number of opening and closing switching exceeds the opening and closing frequency threshold is divided into an abnormal closing time period, and the switching number statistics result is obtained;

[0029] Based on the statistical results of the switching times, the discharge response detection is performed on the time period that remains in the open state, and the time period when the material does not flow or the sensor continuously feeds back the blocking signal is divided into the abnormal blocking time period. The Boolean state marks of abnormal closure, abnormal blocking and corresponding normal operation are set to construct the Boolean state sequence during the operation of the feed port.

[0030] As a further solution of the present invention, the step of obtaining the feed port blockage state warning signal is specifically as follows:

[0031] Based on all the collected opening and closing signals, the Boolean difference method is used to compare the differences between the Boolean state sequences in the past and the current operation stages, and the frequency of Boolean state transitions newly added to the Boolean state sequence in the current operation stage compared with the Boolean state sequence in the historical operation stage is calculated to identify whether the material blocking phenomenon shows an abnormally increasing trend;

[0032] From the statistical frequency of the Boolean state transitions, the section where the abnormal strengthening trend first appears is extracted as the initial point of the material blockage anomaly. The duration and time interval distribution of the subsequent abnormal strengthening trend are statistically analyzed to determine whether the material blockage state is an instantaneous fluctuation or a continuous anomaly. An early warning signal for the material blockage state at the feed port is generated for intervention management of the feeding link of the concrete mixing station.

[0033] Compared with the prior art, the advantages and positive effects of the present invention are:

[0034] In this invention, by periodically assigning status labels for concrete material inventory balances and generating time series, a dynamic label mapping relationship can be established for concrete material inventory management, enhancing the coupling between inventory status and consumption trends. In the process of using the state label sequence to deduce future state change paths, frequency statistics and transition probability modeling between label pairs are used to give inventory change trend predictions data-driven evolutionary capabilities, improving the adaptability and foresight of the prediction. Regarding conveyor belt operating status analysis, the normalized vector form of the operating parameters tension, belt speed, and motor load is used to generate operating trajectories for continuous time periods in potential energy space. This allows the operating status to be concretely expressed in multidimensional space and jamming trends to be monitored, enhancing the accuracy of abnormal state identification. By calculating the potential energy density and density gradient changes within the local neighborhood, the degree of aggregation of the conveyor belt operation can be deeply analyzed. In combination with inventory change trends, the conveyor belt operating mode can be adjusted in a coordinated manner to achieve coordinated control between the concrete material transportation path and inventory dynamics. Furthermore, a Boolean state sequence is constructed using on-off signals, and the actual operation signals are mapped to the feeding process logic flow, allowing for a structured representation of the fluctuation characteristics of the feeding process. Comparing historical and current Boolean state sequence changes can capture the persistent strengthening characteristics of material blockage and enable proactive identification of blockage trends. The overall processing logic, from concrete material consumption statistics to conveyor belt behavior control and feed anomaly warning, integrates a full chain of linkage. This establishes a multi-dimensional interactive feedback mechanism across time, space, and state evolution, significantly enhancing the concrete batching plant's proactive sensing and intelligent scheduling capabilities. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 It is a system flow chart of the present invention. DETAILED DESCRIPTION

[0036] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0037] See also Figure 1 , an information-based concrete mixing station management system includes:

[0038] The inventory status recognition module obtains the total daily concrete material consumption of the concrete mixing station and calculates the corresponding concrete material inventory balance. It assigns status labels to the concrete material inventory balances according to fixed time periods to obtain a status label sequence.

[0039] The state transition deduction module extracts state label pairs of adjacent time periods in the state label sequence, predicts the future change path of the concrete material inventory balance, and obtains the inventory change prediction result;

[0040] The operation potential energy mapping module obtains the operating parameters of the mixing station conveyor belt and performs normalization processing, maps them to the potential energy space in chronological order, and constructs the conveyor belt potential energy distribution map;

[0041] The potential energy trend identification module divides the potential energy distribution map of the conveyor belt into multiple local neighborhoods, calculates the local potential energy density within the local neighborhood to identify the operating status of the conveyor belt, and adjusts the operating mode of the conveyor belt based on the inventory change prediction results to obtain the conveyor belt control results;

[0042] The Boolean sequence construction module collects the opening and closing signals of the mixing station feed port in real time based on the conveyor belt control results after the conveyor belt is adjusted, and constructs the Boolean state sequence during the feed port operation;

[0043] The feed inlet abnormality analysis module compares the Boolean state sequences of the history and the current operation stage based on the collected opening and closing signals, determines the different blockage states of the feed inlet, and generates a feed inlet blockage state warning signal.

[0044] The specific steps for obtaining the state label sequence are:

[0045] Obtain the total daily concrete material consumption of the concrete mixing station, calculate the corresponding concrete material consumption in each time period according to a fixed time cycle, and compare it with the concrete material inventory balance of the mixing station in the corresponding time period to obtain the comparison results of concrete material consumption and balance;

[0046] Total daily concrete material consumption is determined by collecting statistics at fixed time intervals. For example, a batching plant might be set to collect concrete material consumption every hour. By recording hourly concrete production, the specific amount of concrete material consumed during each time period can be determined. This hourly material consumption data is collected and stored in a database. This consumption data is then compared with the concrete material inventory remaining during that time period. For example, suppose 200 tons of cement are consumed at the end of a certain time period (e.g., 9:00 AM to 10:00 AM), while the cement inventory at the beginning of the time period was 500 tons. Comparing the cement inventory with the consumption data determines whether the current inventory is sufficient to meet subsequent production needs. If only 300 tons of cement remain, replenishment may be necessary in the coming period. After the next inventory replenishment (e.g., at 12:00 PM), the system updates the inventory data and re-analyzes the comparison. This hourly comparison allows real-time monitoring of concrete material consumption during concrete production and ensures adequate inventory.

[0047] The comparison results of concrete material consumption and surplus in each time period are assigned different status labels of concrete material inventory surplus. The status labels include sufficient, critical, and shortage. All status labels are integrated to obtain a status label sequence.

[0048] Based on the comparison of concrete material consumption and inventory balance within each time period, different concrete material inventory balance status labels are assigned. Assume that the status labels are assigned according to the following rules: Sufficient: When the inventory balance is greater than a preset percentage of consumption (for example, inventory balance ≥ 150% of consumption), the label is "Sufficient"; Critical: When the inventory balance is close to consumption and approaches the safety warning line (for example, inventory balance is between 100% and 150%), the label is "Critical"; Shortage: When the inventory balance is below a certain threshold of consumption (for example, inventory balance ≤ 100% of consumption), the label is "Shortage".

[0049] Assume that the concrete material consumption in each time period is (i represents the time period number), concrete material inventory balance at the mixing station ,in and Respectively represent the consumption and inventory balance from the 1st to the nth time period, using the formula: , calculate the comparison value of the i-th time period ;

[0050] According to the comparison value The mapping tags are as follows: , the status is "sufficient"; if , then the state is "critical"; if , the status is "out of material".

[0051] For example, suppose the cement consumption in the first hour is Tons, inventory balance is Tons, then the comparison value , the status is "sufficient"; the consumption in the second hour Tons, inventory balance is Tons, then , the status is "critical"; the consumption in the third hour Tons, inventory balance is Tons, then , the status is "out of stock". The final status label sequence is: 1st hour - sufficient; 2nd hour - critical; 3rd hour - out of stock.

[0052] The results show that by calculating the ratio of consumption to inventory within each time period, we can intuitively determine the current material status and quantify this status into standardized labels, providing directly usable input conditions for subsequent data processing, state sequence integration, and other operations. Status labels clearly reflect the inventory status of concrete materials within each time period, allowing timely identification of inventory issues and appropriate adjustments.

[0053] By comparing concrete material consumption within a fixed time period with the concrete material inventory balance during the corresponding time period and assigning status tags based on the comparison results, dynamic grading and continuous labeling of inventory status can be achieved, shifting inventory management from static inventory monitoring to dynamic status identification. By forming a state tag sequence covering the entire time period, the evolving relationship between concrete material consumption and balance can be fully reflected, providing data support for subsequent inventory trend forecasting, raw material replenishment scheduling, and equipment operation adjustments, thereby improving the real-time and precision of inventory management.

[0054] The specific steps for obtaining inventory change forecast results are as follows:

[0055] Extract state label pairs from adjacent time periods in the state label sequence, compare the state label contents of the state label pairs from adjacent time periods, determine whether the state has changed, count the transition frequencies of each state change in all time periods, and construct a state label transition frequency table;

[0056] According to the obtained state label sequence "1st hour - sufficient, 2nd hour - critical, 3rd hour - short of food", assuming that the state label of the 10th hour is extracted, the extended complete sequence is: 1st hour - sufficient, 2nd hour - critical, 3rd hour - short of food, 4th hour - short of food, 5th hour - critical, 6th hour - critical, 7th hour - sufficient, 8th hour - sufficient, 9th hour - critical, 10th hour - short of food, extract the state label pairs in adjacent time periods, including "sufficient - critical", "critical - short of food", "short of food - short of food", "short of food - critical", "critical - critical", "critical - sufficient", "sufficient - sufficient", "sufficient - critical", and "critical - short of food". Compare these label pairs one by one to determine whether the adjacent states have changed. Among the above 9 pairs of label relationships, "sufficient - critical" has no change. "critical-material shortage", "material shortage-critical", "critical-sufficient", "sufficient-critical", and "critical-material shortage" are situations where state changes occur, while "material shortage-material shortage", "critical-critical", and "sufficient-sufficient" are situations where the state does not change. The number of state transitions is counted, and a state label transfer frequency table is constructed. Taking "sufficient, critical, and material shortage" as the state set, the following frequency statistics are obtained through pair-by-pair analysis: from "sufficient" to "critical" appears 2 times, from "critical" to "material shortage" appears 2 times, from "material shortage" to "material shortage" appears 1 time, from "material shortage" to "critical" appears 1 time, from "critical" to "critical" appears 1 time, from "critical" to "sufficient" appears 1 time, from "sufficient" to "sufficient" appears 1 time, and from "sufficient" to "sufficient" appears 1 time. The state transition frequencies that do not appear are all recorded as 0, and finally a complete state label transfer frequency table is formed.

[0057] Initialize the Markov chain model and input the state label transfer frequency table into the Markov chain model. The Markov chain model constructs the corresponding state label transfer probability matrix to predict the transfer probability of the state label of the current concrete material inventory balance to the state label of other concrete material inventory balances in multiple future time periods, and obtain the future transfer probability prediction results;

[0058] A Markov chain model is a mathematical model used to describe the probabilistic transitions of system states between different time points. Its basic structure consists of three core elements: a state set, a state transition probability matrix, and an initial state distribution. The state set is a finite set of all possible system states within the model, such as "sufficient," "critical," and "out of stock" in inventory management. The state transition probability matrix describes the probability of a transition between any two states within a time step. Each row corresponds to a current state, and each column represents a possible target state. The sum of the elements in each row of the matrix is ​​1. The initial state distribution is the probability of the system being in each state when the model begins running.

[0059] Let the state set be , assuming that according to the statistical state label transfer frequency, the state label transfer frequency matrix is ​​constructed as follows: the frequency from "sufficient" to "sufficient" is 1, "sufficient" to "critical" is 2, and "sufficient" to "shortage" is 0; from "critical" to "sufficient" is 1, "critical" to "critical" is 1, and "critical" to "shortage" is 2; from "shortage" to "sufficient" is 0, "shortage" to "critical" is 1, and "shortage" to "shortage" is 1.

[0060] Use the dtmc toolkit in MATLAB software to perform the Markov chain modeling process, input the above state label transfer frequency matrix as the state transfer data of the Markov chain model, and construct the state label transfer probability matrix ,First, let the state set be set. The state transition frequency matrix is ​​obtained ,through the statistics of the historical state sequence label pairs. The ,transition frequency of each state is obtained by traversing the adjacent state label pairs in ,the time series and recording the number of transitions between ,each state.

[0061] In the Markov chain model, the current state is the first state Transition to the second state The probability of : ;in, Indicates the first state in the state label transfer frequency table Transfer to the second state frequency; Indicates the first state in the state label transfer frequency table The sum of the frequencies of all possible transitions, i.e. the first state The total number of transfers; Used to represent all second states Enumeration variable of; It is the total number of states in the state label transfer frequency table, indicating that the state set includes the three states of "sufficient", "critical" and "out of stock".

[0062] Let the state set be . According to the state label transfer frequency statistics obtained in paragraph 1, the state label transfer frequency matrix is ​​constructed as follows: the frequency from "sufficient" to "sufficient" is 1, "sufficient" to "critical" is 2, and "sufficient" to "shortage" is 0; from "critical" to "sufficient" is 1, "critical" to "critical" is 1, and "critical" to "shortage" is 2; from "shortage" to "sufficient" is 0, "shortage" to "critical" is 1, and "shortage" to "shortage" is 1.

[0063] Take the state "sufficient" as the initial state as an example:

[0064] Count the frequency of its transition to other states: , , , the total transfer frequency is: ,but: .

[0065] Similarly, calculate the "critical" state transition probability: , , , the total frequency is , corresponding probability: .

[0066] For the "Out of Material" status: , , , the total frequency is , corresponding probability: .

[0067] Finally, the state transition probability matrix is ​​formed : .

[0068] The current state is "lack of material", that is, the state vector at the 10th hour is: ;

[0069] Using the first-order Markov state transition formula:

[0070]

[0071] in, It is The state distribution vector of the hour is of length The row vector of represents the probability distribution of the system in each state at the current time point. For example, Indicates that it is completely in a "lack of material" state; It is The hourly state distribution prediction results indicate the probability of transitioning from the current state to the "sufficient", "critical" and "insufficient" states at the next moment; is the state transition probability matrix, with dimension , where each row corresponds to a current state, each column represents a possible target state to transfer to, and each element Indicates the slave state Transfer to state The process of multiplying the state vector and the transfer matrix indicates that starting from the current distribution, the weights corresponding to each possible target state are superimposed to obtain the state probability at the next moment.

[0072] 11th hour prediction process:

[0073] The initial probability vector is the 10th hour and the status is material shortage. , multiplied by the state transition probability matrix : ;

[0074] First item (sufficient): ;

[0075] Second term (critical): ;

[0076] Item 3 (missing material): .

[0077] The result is: .

[0078] This means that at the 11th hour, the probability of being in the "critical" state is 0.5, the probability of being in the "shortage" state is 0.5, and the probability of being in the "sufficient" state is 0.

[0079] 12th hour prediction process:

[0080] State vector based on the 11th hour , continue to use the state transition formula:

[0081]

[0082] First item (sufficient): ;

[0083] Second term (critical): ;

[0084] Item 3 (missing material): .

[0085] therefore: .

[0086] It means that at the 12th hour: there is a 12.5% ​​probability of being in the "sufficient" state; a 37.5% probability of being in the "critical" state; and a 50% probability of being in the "shortage" state.

[0087] This distribution indicates that inventory shortages will remain dominant for a short period of time (primarily due to material shortages), but the increasing criticality indicates a slight stabilization of the system, while the likelihood of sufficient inventory remains low. This state forecast can provide a basis for inventory replenishment scheduling, suggesting the need to organize restocking before the 12th hour.

[0088] The calculation of the state transition probability matrix is ​​obtained by counting the transition frequencies between each state in the historical state label sequence. This process can quantify the discrete historical state change behavior into a systematic probability relationship. The calculation logic of the first-order Markov state transition formula is based on the state distribution vector at the current moment and the state transition probability matrix Multiply them together to get the predicted distribution of the state at the next moment , indicating that the system's next state depends solely on the current state, and is calculated based on the probability of transitioning from the current state to each target state. Through this process, the model not only predicts the probability of different states within any future time period but also reveals the trend of system state changes, providing quantitative support for decisions such as inventory control, material replenishment, and risk warning.

[0089] Based on the future transfer probability prediction results, the future change path of the concrete material inventory balance is identified. The future change path includes the continuous shortage of concrete material inventory balance, the rebound to the critical state, and the gradual recovery to the sufficient state, thereby obtaining the inventory change prediction results;

[0090] First, the state transition vector generated based on the 10th hour state "lack of material" , it can be seen that after entering the 11th hour, the concrete material inventory status has two equally probable evolution directions, that is, the probability of maintaining the "material shortage" state is 50%, and the probability of slowly recovering to the "critical" state is also 50%. Under this prediction condition, the system is in an unstable and fluctuating state. The coexistence of material shortage and criticality means that the risk of inventory shortage still exists, but there are some signs of stabilization. Continuing to predict for the 12th hour, we get The distribution of state transition probabilities changes further, with the "material shortage" state still accounting for the largest proportion, maintaining 50%, but the "critical" state rises to 37.5%, indicating that concrete material inventory is in a continuous recovery process. Although the "sufficient" state only accounts for 12.5%, it has begun to appear. From the perspective of the evolution path of the material shortage state, the most likely paths are "material shortage → material shortage → material shortage" or "material shortage → critical → material shortage". There is also a certain probability of "material shortage → critical → critical" or "material shortage → critical → sufficient". If the future state path enters the continuous evolution of "material shortage → material shortage → material shortage", it means that no replenishment measures have been taken and the risk will continue. If it enters the "material shortage → critical → sufficient" path, it indicates that the inventory will gradually return to stability. The current forecast results do not show a strong inventory recovery signal. Therefore, the change path shows a "shock recovery" trend. It is necessary to further extend the forecast period or increase the transition probability of the intermediate state to achieve the return of the inventory safety state, so as to finally obtain the trend forecast result of inventory changes.

[0091] By extracting the relationship between state changes in adjacent time periods within a state tag sequence and counting the frequency of state transitions, the evolutionary patterns of concrete material inventory status can be established. By constructing a state transition probability matrix using a Markov chain model, quantitative predictions of inventory status trends over multiple future time periods are achieved, enabling concrete material management to identify trends and predict evolutionary paths. By identifying the future paths of inventory balance changes, trends such as shortages and recovery can be detected in advance, enhancing inventory management's foresight and decision-making support capabilities, and preventing sudden disruptions to production caused by concrete material shortages.

[0092] The specific steps for obtaining the potential energy distribution diagram of the conveyor belt are as follows:

[0093] Obtaining and normalizing the conveyor belt operating parameters of the mixing station, wherein the conveyor belt operating parameters include the conveyor belt tension, belt speed, and motor load, and obtaining the processed conveyor belt operating parameters;

[0094] First, corresponding sensors were deployed at key locations in the concrete mixing station's conveying system to enable real-time acquisition of conveyor belt operating parameters. Belt tension was measured using strain-gauge tensile sensors installed on both sides of the belt tensioning device. These sensors output an electrical signal proportional to the belt tension. Belt speed was determined using rotary encoders installed at the ends of the belt's drive or return pulleys. These encoders indirectly reflect the belt's linear speed by recording the number of rotational pulses per unit time. Motor load data was collected using a combination of current and voltage sensors installed on the input cable path of the main drive motor. These sensors read the motor's current and voltage in real time and output data frames. All three types of sensors were connected to a data acquisition module with an acquisition cycle set to every 5 seconds. The collected data was then imported into a data management platform for normalization. This normalization process utilized Python's pandas and sklearn libraries. The standardized data preprocessing module independently converted the tension, belt speed, and motor load data into standardized values ​​ranging from 0 to 1. This normalization process was performed separately for each parameter type, and the standardized results served as input for subsequent operational status analysis.

[0095] The processed conveyor belt operating parameters of each time period are combined into corresponding vector forms and mapped to the potential energy space in chronological order. In the potential energy space, the conveyor belt operating parameters represent the conveyor belt operating status points in each time period, and the conveyor belt potential energy distribution map is constructed;

[0096] The processed conveyor belt operating parameters of each time period are combined into corresponding vector forms. The normalized tension, belt speed, and motor load data in each time period are combined into a three-dimensional column vector according to a unified timestamp. The vector form is expressed as follows: ;in, Indicates the conveyor belt operating parameters after processing. The conveyor belt operation state vector for a time period is dimensionless. 、 、 The conveyor belt operating parameters after processing are The normalized values ​​of tension, belt speed and motor load in each time period. This three-dimensional vector is used to accurately describe the multi-dimensional state characteristics of the conveyor belt at that time point. They are arranged in chronological order and mapped to a potential energy space. In potential energy space, tension represents the strength of the belt's tension and reflects the stress level in the belt tensioning system. Excessive tension may indicate overload, while low tension may indicate belt slippage or slack. Belt speed represents the linear velocity of the conveyor belt, representing the material throughput rate per unit time. Changes in belt speed can reveal whether the belt is operating smoothly. Motor load represents the energy consumption of the drive system and is often closely related to transmission resistance and load magnitude. Fluctuations in motor load may indicate mechanical anomalies or fluctuating operating conditions. These three-dimensional parameters correspond to the X, Y, and Z axes of the spatial coordinate system in potential energy space: tension as the X-axis component, belt speed as the Y-axis component, and motor load as the Z-axis component. Each operating state point in each time period is uniquely located in three-dimensional space by this three-dimensional vector, forming a state trajectory that continuously evolves over time. Furthermore, by performing three-dimensional spatial interpolation and density analysis on the set of all operating state points, a potential energy distribution map of the conveyor belt's operating state can be constructed. This can be used to visualize operating stability, identify areas of high energy consumption or high stress concentration, and complete a temporal spatial representation of the conveyor state. The construction and visualization of this graph can be achieved using MATLAB's plot3 and surf functions or Python's matplotlib library's Axes3D.plot and plot_surface functions. If higher interactivity and display accuracy are required, Plotly's scatter3d and surface modules can also be used. During the drawing process, different color gradients can be assigned to state points in different time periods to enhance the recognition of the operation evolution rhythm, thereby ultimately generating a complete conveyor belt potential energy distribution map.

[0097] By normalizing multiple operating parameters, such as conveyor belt tension, belt speed, and motor load, and mapping them into potential energy space as vectors, the conveyor belt's operating status at each time period can be visualized as potential energy state points, thereby constructing a complete conveyor belt trajectory map. This approach captures the inherent correlations between operating parameters, reveals the evolutionary trends of equipment operating status, enhances the ability to analyze conveyor belt dynamic behavior, and provides a multi-dimensional basis for anomaly detection and control strategies.

[0098] The specific steps for obtaining the conveyor belt control results are as follows:

[0099] Based on the potential energy distribution map of the conveyor belt, the conveyor belt running state points are divided into multiple local neighborhoods according to the distance in the potential energy space according to the comparison result, and the local neighborhood division result is obtained;

[0100] Based on the operating state points mapped to the potential energy space, the distance measurement method between points in three-dimensional Euclidean space is adopted. With each state point as the center, a spatial radius threshold is selected. Within the radius, all neighboring state points whose distance from the center point does not exceed the radius threshold are extracted to form a local neighborhood set corresponding to the point. The distance calculation adopts the Euclidean distance formula in three-dimensional space. According to the ternary coordinates composed of the normalized values ​​of tension, belt speed and motor load of each point as input, the spatial distance between any two points is calculated in batches, and then each point is subjected to neighborhood clustering. In the process, the KDTree structure of the scipy library in Python is used to realize fast neighbor search. A corresponding neighborhood point set is formed for each state point, and the number of state points contained in each group of neighborhoods is recorded. After all state points have completed the neighborhood division, a local neighborhood set automatically grouped according to the density of spatial position is obtained.

[0101] Calculate the three-dimensional Euclidean distance between any two conveyor belt operating state points in the potential energy space using the following formula:

[0102]

[0103] in, Indicates the potential energy distribution diagram of the conveyor belt. The conveyor belt running status point and the The Euclidean distance (dimensionless) between the running state points of the conveyor belt in the potential energy space, that is, the position difference in the tension-belt speed-load three-dimensional system; are the serial indexes of the conveyor belt operating status points in the conveyor belt potential energy distribution diagram, representing the operating status points sampled at different time periods; They are and The corresponding tension normalized value; They are and The corresponding normalized value of the belt speed; They are and The corresponding normalized value of the motor load.

[0104] Based on vector representation: , assuming that the first state point , sampling time period If it is 09:00 Specifically, at 09:00, the tension is 0.60 (normalized), the belt speed is 0.80, and the motor load is 0.45. The second state point , sampling time period 09:05 Specifically, at 09:05, the tension is 0.70 (normalized), the belt speed is 0.65, and the motor load is 0.50. The third state point , sampling time period 09:10 Specifically, the tension at 09:10 is 0.62 (normalized), the belt speed is 0.78, and the motor load is 0.40.

[0105] Calculate the Euclidean distance between the first state point 1 and the second state point 2 in the potential energy space:

[0106] ;

[0107] Calculate the Euclidean distance between the first state point 1 and the third state point 3 in the potential energy space:

[0108] ;

[0109] Calculate the Euclidean distance between the second state point 2 and the third state point 3 in the potential energy space:

[0110] ;

[0111] The neighborhood judgment threshold can be based on the distance distribution curve of all point pairs, and the minimum 10% value can be selected as the reference threshold of the adjacent area. It can also be tested by multiple groups of normal and abnormal data, and the maximum spatial span in the clustering area can be observed. The upper limit of the maximum span is used as the reference threshold of the adjacent area. It is assumed that the local neighborhood threshold is set. , which means that when the three-dimensional distance between two state points is less than this value, they can be considered to have similar operating states and belong to the same local neighborhood. → belong to the same neighborhood; → belong to the same neighborhood; → belong to the same neighborhood. The results show that the distances between the three state points all meet the neighborhood conditions, indicating that the fluctuation range of their operating characteristics in the three dimensions of tension, speed, and load is small, indicating that the conveyor belt operation is stable during this period and the parameters are consistent.

[0112] By calculating the normalized parameters and Euclidean distance of specific operating status points, it is possible to intuitively reflect whether the operating status of the conveyor belt in different time periods is significantly different. If the distances between multiple points are within the threshold, it can be considered that these points belong to the same operating mode in space. Subsequently, density calculation and trend judgment can be performed based on this neighborhood.

[0113] Based on the local neighborhood division results, the local potential energy density of each conveyor belt operation status point in its corresponding local neighborhood is calculated. The aggregation degree and density gradient change of each conveyor belt operation status point are analyzed according to the local potential energy density, and the corresponding density area boundaries are divided.

[0114] Calculate the The conveyor belt running state point in its corresponding local neighborhood The local potential energy density within The (dimensionless) formula is as follows:

[0115]

[0116] in, Is the sum index range, indicating the The conveyor belt running state points correspond to the local neighborhood All other items except itself Conveyor belt operation status points; It is a natural exponential function, which is used to perform exponential decay on the square of the distance; It represents the potential energy distribution diagram of the conveyor belt. The conveyor belt running status point and the The Euclidean distance between the conveyor belt running state points in the potential energy space; It is a kernel width parameter used to regulate the decay rate of the exponential function in the calculation of local potential energy density. It controls the amplitude of density decay. The value is determined by the range of structural changes in the density area. For example, it can be determined by analyzing the median of the distance distribution between multiple batches of sample point pairs. For example, it can be preliminarily screened using the statistical standard deviation of batch running data, and then repeatedly verified and selected through neighborhood aggregation comparison experiments.

[0117] The first state point is known With the second state point Euclidean distance in potential energy space: ; The first state dot With the third state point Euclidean distance in potential energy space: ; The second state point With the third state point Euclidean distance in potential energy space: ,

[0118] Calculate state points In the neighborhood Density: ;

[0119] Calculate state points In the neighborhood Density: ;

[0120] Calculate state points In the neighborhood Density: .

[0121] It is known that the local potential energy density of each conveyor belt operating state point is: State point 1 (09:00) is , state point 2 (09:05) is , state point 3 (09:10) is .

[0122] By comparing the density values, we can conclude that state point 3 has the highest density and is the most concentrated point in the local neighborhood, which can be regarded as the dense center; state point 1 has the second highest density and is located in a relatively concentrated area, close to the density peak point; state point 2 has the lowest density, is far away from the aggregation core, and is in the sparse edge area.

[0123] Calculate the density difference between any two state points as the local density gradient value:

[0124]

[0125]

[0126]

[0127] The results show that the density drops sharply from state point 3 to state point 2, with a clear density gradient. State points 1 and 3 have similar densities, belonging to the same high-density or slowly changing region. There is also a clear downward trend from state point 1 to state point 2. Therefore, state point 2 is a candidate for a boundary point, state point 3 is a clustering center, and state point 1 is a transition or secondary center.

[0128] Use the average density and standard deviation of the current three points as the basis for boundary classification:

[0129] Average density : ;

[0130] Standard deviation (approximate):

[0131] .

[0132] According to the density distribution analysis method commonly used in statistics, the state point density is divided into the following three categories:

[0133] High-density area: local potential energy density value ;

[0134] Medium-density areas: ,Right now ;

[0135] Low-density areas: .

[0136] result : Falling into the medium-density area, tending to high values, it is judged to be inside the cluster; : Belong to the medium-density area, and the degree of aggregation is close to point 3; : Points below the low-density threshold are considered to be outside the boundary. The medium-density region is composed of multiple adjacent high-density state points and is a localized cluster. The low-density region is a region with fewer sparsely distributed points and has boundary characteristics. The region boundary is drawn from the medium-density to the low-density gradient descent direction, forming a segmentation surface.

[0137] The calculation logic of local potential energy density is based on the relative distance relationship between a state point and other state points in its neighborhood in the potential energy space. By performing an exponential function-weighted summation of the Euclidean distances between each state point and other points in the neighborhood, the degree of clustering of the state point in the local space is obtained. The higher the density, the more neighboring state points there are around the point and the more concentrated their distribution; the lower the density, the fewer neighboring points there are around the point or the distribution is more sparse. This calculation logic not only reflects the local clustering characteristics of a single state point in space, but also provides a quantitative basis for subsequent density gradient analysis and boundary demarcation. In the potential energy space, the difference in local potential energy density values ​​can reveal the structural relationship between clustered areas, transition areas, and boundary areas, thereby effectively identifying the clustering characteristics and evolution trends of the operating state.

[0138] Obtain the position of the conveyor belt operating parameters in the potential energy space, calculate the spatial position offset between consecutive time periods, determine the offset trajectory based on the spatial position offset, compare the offset trajectory with the density area boundary, and use the comparison result to identify whether the conveyor belt operating state is migrating towards a blocking trend;

[0139] After obtaining the position of the conveyor belt operating parameters in the potential energy space, the operating status point of each time period is mapped to the potential energy space as a three-dimensional coordinate point according to the three-dimensional vector composed of the normalized tension, belt speed and motor load corresponding to each time period. For example, the status points at 09:00 are 0.60, 0.80, and 0.45; at 09:05, they are 0.70, 0.65, and 0.50; and at 09:10, they are 0.62, 0.78, and 0.40. These points constitute the spatial trajectory within the continuous time period. Subsequently, based on the vector coordinate difference between each two adjacent time points, the Euclidean distance is used to calculate its offset. For example, the offset from 09:00 to 09:05 is 0.187, and from 09:05 to 09:10 is 0.182, thereby establishing a complete trajectory segment sequence. Next, the trajectory line is spatially overlapped with the previously delineated density region boundary, and the region of each state point is determined in the potential energy space. For example, the densities at 09:00 and 09:10 are 1.339 and 1.359 respectively, both in the medium density region, while the density at 09:05 is 0.854, falling into the low density region. Therefore, the trajectory line is located in the medium density region from 09:00, then deviates to 09:05 when it crosses the medium density boundary and enters the low density region, and then deviates to 09:10 when it returns to the medium density region. The comparison process confirms that the state at 09:05 has "out-of-bounds" behavior, that is, it shifts to the low-density extension. This out-of-bounds phenomenon indicates that the conveyor belt operating parameters fluctuated greatly during this period, including abnormal combinations such as increased tension, reduced belt speed, and increased motor load, which caused the operating state to move away from the stable aggregation area, indicating that the conveyor system had potential jamming characteristics or signs of unstable operation during this time period. The subsequent rebound of the trajectory to the medium-density area can be regarded as a self-recovery performance of the system, but "out-of-bounds" is an early sign of a key jamming trend and needs to be monitored and identified.

[0140] Combining the results of the conveyor belt operation status analysis and the future change path of the concrete material inventory balance in the inventory change forecast results, the conveyor belt operation mode is adjusted based on the conveyor belt operation status and future inventory balance to obtain the conveyor belt control results;

[0141] Combined with the prediction results of the future change path of the concrete material inventory balance, the conveyor belt operation mode is adaptively adjusted in various scenarios according to the actual deviation trajectory of the conveyor belt operation status. For example, when the operation status is in a stable range, that is, the potential energy space trajectory has not deviated from the medium and high density area, but the forecast shows that the future inventory balance will continue to decrease and approach the "material shortage" state, the conveyor belt operation mode can be adjusted to the deceleration mode, reducing the conveyor belt speed or intermittent operation to avoid no-load operation when the material is insufficient; for example, the current operation status of the conveyor belt shows frequent deviations and has continuously "out of bounds". " phenomenon, indicating an abnormal operating trend, but the concrete material inventory will remain "sufficient" in the next few time periods. At this time, the steady load and slow delivery mode should be adopted, the belt speed should be appropriately reduced, and the operation monitoring interval should be increased to reduce high-load transmission under abnormal conditions. For example, if the current conveyor belt operation is stable and the inventory will also be sufficient in the future, the current operation mode can be maintained or the belt speed can be increased according to the plan to improve material turnover efficiency. On the contrary, if the conveyor belt operation is unstable and the inventory forecast shows a downward trend, a dual protection mode should be adopted, combining speed limit operation and intermittent control to avoid the dual risks of transmission failure and resource waste. Through responsive adjustments to the above-mentioned multiple combinations, the transmission system can be coordinated and linked with the inventory change trend to ensure the safety of the material transportation process and the rationality of resource utilization.

[0142] By dividing the operating status points in the potential energy distribution diagram into local neighborhoods based on distance and calculating the local potential energy density, we can identify the clustering characteristics and density gradient changes of the operating status points, clarify the potential energy concentration areas and boundaries, and enhance the spatial recognition of conveyor belt operation stability. Furthermore, by combining the position offsets in the time series and constructing continuous offset trajectories, and comparing them with the density boundaries, we can accurately determine whether the operating status is evolving towards a blocking trend. Based on this judgment and the inventory change path, the conveyor belt operation mode is adjusted to achieve coordinated optimization of conveyor belt behavior and inventory status, improving conveyor efficiency and effectively avoiding operational anomalies.

[0143] The steps for obtaining the Boolean state sequence are as follows:

[0144] Based on the results of conveyor belt control, the opening and closing signals of the mixing station feed port after the conveyor belt adjustment are collected in real time. The opening and closing signals are counted according to the number of switching operations within a specified time. By setting the opening and closing frequency threshold, the time period when the number of opening and closing switching exceeds the opening and closing frequency threshold is divided into the abnormal closing time period, and the switching number statistics are obtained;

[0145] The opening and closing status of the mixing station feed inlet is collected in real time during each time period. The collection method is to obtain the open and closed state change signals through the Hall effect sensor or reed switch device installed on the feed mechanism, and record the number of switching times within the set time period to form the opening and closing action statistics. At the same time, an opening and closing frequency threshold is set as the judgment benchmark. The threshold is set based on the maximum opening and closing action frequency allowed by the feed inlet mechanical structure. This value is usually provided by the equipment manufacturer, but it can also be obtained through empirical data obtained through long-term on-site operation monitoring. For example, under normal operation, the opening and closing times are collected continuously for 30 time periods per day, and the average frequency and variance range are calculated. After excluding special operating conditions, the highest value in the stable frequency band is extracted as a reference value and set as the opening and closing frequency threshold. For example, if the average opening and closing frequency within a 60-second statistical period is 3.2 times and the maximum stable value is 4.5 times, the opening and closing frequency threshold can be set to 5 times / minute. When the number of opening and closing switches in a certain time period exceeds this threshold, it indicates that there is a high-frequency opening and closing phenomenon in that time period, which is judged as frequent switching actions triggered by equipment abnormality. The time period is classified as an abnormal closed state.

[0146] Based on the statistical results of the switching times, the discharge response detection is performed on the time period that remains in the open state. The time period when the material does not flow or the sensor continuously feeds back the blocking signal is divided into the abnormal blocking time period. The Boolean state flags of abnormal closing, abnormal blocking and corresponding normal operation are set to construct the Boolean state sequence during the operation of the feed port.

[0147] Perform discharge response detection on the time period that remains open. First, filter out the time period in which the feed port is continuously in the "open" state within the statistical period. For example, if the opening and closing signals do not switch during the time period from 09:02 to 09:03, it is determined that the period is in a continuously open state. Then call the material flow sensor (such as an infrared photoelectric switch or a weighing induction plate) located below the feed port to record whether the material flows. If the sensor continuously detects zero flow or no change in value during the entire time period, check whether the pressure sensor feedback signal on the side wall of the feed port is continuously in a high value state, indicating that the material is blocked. If the feed port is released, the time period is identified as the material not completing the unloading process in the open state. According to the feedback from the dual sensors, the time period is determined to be an abnormal blockage state. This identification method avoids misjudgment due to a single signal error. Finally, the abnormal blockage time period is set to a Boolean value of "0", which is also marked as an abnormal state like the aforementioned abnormal closing state. Other time periods that are continuously open and detect normal unloading flow are marked as a Boolean value of "1", indicating that the feed port is in a normal working state during this period. The status marks of all time periods are integrated in chronological order to form a complete Boolean state sequence during the operation of the feed port.

[0148] By collecting and counting the switching frequency of the feed port opening and closing signals in real time, abnormal closing events can be efficiently identified, and abnormal conditions can be accurately marked by setting opening and closing frequency thresholds. At the same time, the flow of materials remaining in the open state is monitored, and any blockages detected are promptly identified and marked as abnormal. Converting this status information into a Boolean state sequence clearly displays the operating status of the feeding process, improving the monitoring and early warning capabilities of feed port anomalies, facilitating early intervention and reducing the risk of production interruptions.

[0149] The specific steps for obtaining the early warning signal of the feed port blockage state are as follows:

[0150] Based on all the collected opening and closing signals, the Boolean difference method is used to compare the differences between the Boolean state sequences of the historical and current operating stages. The frequency of new Boolean state transitions in the Boolean state sequence of the current operating stage compared to the Boolean state sequence of the historical operating stage is calculated to identify whether the blockage phenomenon shows an abnormally increasing trend.

[0151] Assume that the Boolean state sequence of the historical operation stage is , the Boolean state sequence of the current running stage is ,in, Indicates the open and closed status of the feed port at each time point during the historical time period (1 for open, 0 for closed), recorded by on-site sensors or derived through historical data. Indicates the open and closed state of the feed port at each time point in the current time period (1 for open, 0 for closed), which is generated by the signal collected by the sensor in real time. The Boolean state difference sequence is expressed as:

[0152]

[0153] in, It is the first Boolean state sequence in the historical operation stage. The Boolean status value of each time period, which can be 0 or 1, is provided by historical operation data; Is the Boolean state sequence of the current running stage The Boolean status value of each time period, which is 0 or 1, is provided by the sensor in real time; It is the total number of Boolean state transitions between the Boolean state sequence of the current operation stage and the Boolean state sequence of the historical operation stage, reflecting the frequency of state changes and used to identify whether the blockage phenomenon is increasing; Is the index of the time period, indicating that the Boolean state in each time period is compared, from 1 to ; Is the total number of time periods, indicating the number of time periods for comparison. For example, if statistics are calculated once per minute, The total number of time periods.

[0154] Assume that there are the following historical Boolean state sequence and current Boolean state sequence: Historical state sequence : [1, 1, 0, 1, 0, 1], current state sequence : [1, 0, 0, 1, 1, 0], calculates the Boolean state difference sequence : , , , , , .

[0155] result: .

[0156] The results show that the Boolean state has changed three times compared to the current state. These changes may be caused by abnormal opening and closing of the feed port or blockage. It is worth further analysis to determine whether there is blockage or other problems.

[0157] By comparing the Boolean state sequences of the historical and current phases on a time-by-time basis, the difference in Boolean state within each time period is calculated—that is, the difference between the historical state and the current state within the corresponding time period. The total number of Boolean state transitions is then calculated by summing the differences across all time periods. This value reflects the frequency of Boolean state changes during the current operating phase compared to historical phases, with a larger value indicating more frequent abnormal state changes. This calculation quantifies state changes during the current operating phase, allowing identification of whether the blocking phenomenon is showing an abnormally increasing trend. A significant increase in the calculated Boolean state differences indicates the possibility of abnormal blocking behavior in the system. In particular, a high frequency of newly added Boolean state transitions suggests that the blocking problem may be intensifying. Therefore, the calculation process of this formula helps to identify potential blocking trends in advance by monitoring Boolean state changes.

[0158] The segment where the abnormal increasing trend first appears is extracted from the statistical Boolean state transition frequency as the starting point of the material blockage anomaly. The duration and time interval distribution of the subsequent abnormal increasing trend are calculated to determine whether the material blockage state is a transient fluctuation or a persistent abnormality. An early warning signal for the material blockage state at the feed port is generated for intervention management of the concrete mixing plant's feeding process.

[0159] First, by analyzing the Boolean state difference sequence, the system detects that the frequency of state transitions within several consecutive time periods exceeds a set threshold, and if this frequency continues to increase along the time axis, it is determined to be the initial point of the abnormal congestion trend. For example, if the frequency of transitions in the Boolean difference sequence during a certain period exceeds the normal fluctuation range of historical data and continues to increase, this period can be determined to be the initial point of the abnormal congestion. Next, the duration and time interval distribution of the subsequent abnormal trend are calculated. By continuously monitoring the next time period, if the frequency of transitions continues to increase and the intervals gradually decrease, it indicates that the congestion phenomenon may have evolved from a temporary fluctuation to a persistent anomaly. Otherwise, it may be a transient fluctuation. The specific duration and time interval can be calculated by comparing the start and end times of the abnormal time period to obtain the duration of each anomaly and the interval between anomalies. If the anomaly duration is long and the interval is short, the trend is likely a persistent congestion state. If the abnormal fluctuations occur only in short time periods and the intervals are long, it can be classified as a transient fluctuation. Based on the analysis results and the preset warning values ​​of historical data, an early warning signal for the feed port blockage status is generated. When the blockage status shows a persistent abnormality, the system will trigger an early warning and issue an alarm to the operator, indicating that intervention management may be required. Appropriate measures such as adjusting the opening and closing mode of the feed port and reducing the conveyor belt speed can be taken to avoid the impact of blockage on the production process and ensure the normal operation and efficient operation of the mixing station.

[0160] By comparing historical and current Boolean state sequences using the Boolean difference method, we can accurately identify the changing trends of feed inlet blockage and calculate the frequency of new state transitions, thereby determining whether the blockage problem is showing an abnormally increasing trend. By extracting the initial point of the abnormal trend and analyzing its duration and time interval, we can determine whether the blockage state is an occasional transient fluctuation or a persistent abnormality. This allows for the timely generation of a blockage warning signal, enabling effective intervention in the concrete mixing plant's feed process, reducing production delays or equipment damage caused by blockage.

[0161] The above are merely preferred embodiments of the present invention and do not limit the present invention in any other form. Any technician familiar with the profession may use the technical content disclosed above to change or modify it into an equivalent embodiment with equivalent changes and apply it to other fields. However, any simple modification, equivalent change and modification made to the above embodiment based on the technical essence of the present invention without departing from the content of the technical solution of the present invention shall still fall within the scope of protection of the technical solution of the present invention.

Claims

1. An information-based concrete mixing station management system, characterized in that: The system includes: The inventory status recognition module obtains the total daily concrete material consumption of the concrete mixing station and calculates the corresponding concrete material inventory balance. It assigns status labels to the concrete material inventory balances according to fixed time periods to obtain a status label sequence. The state transition deduction module extracts state label pairs of adjacent time periods in the state label sequence, predicts the future change path of the concrete material inventory balance, and obtains the inventory change prediction result; The operation potential energy mapping module obtains the operating parameters of the mixing station conveyor belt and performs normalization processing, maps them to the potential energy space in chronological order, and constructs the conveyor belt potential energy distribution map; The potential energy trend identification module divides the potential energy distribution map of the conveyor belt into multiple local neighborhoods, calculates the local potential energy density within the local neighborhood to identify the operating status of the conveyor belt, and adjusts the operating mode of the conveyor belt based on the inventory change prediction results to obtain the conveyor belt control results; The Boolean sequence construction module collects the opening and closing signals of the mixing station feed port in real time based on the conveyor belt control results after the conveyor belt is adjusted, and constructs the Boolean state sequence during the feed port operation; The feed inlet abnormality analysis module compares the Boolean state sequences of the history and the current operation stage based on the collected opening and closing signals, determines the different blockage states of the feed inlet, and generates a feed inlet blockage state warning signal.

2. The information-based concrete mixing station management system according to claim 1 is characterized in that: The steps for obtaining the state tag sequence are specifically as follows: Obtain the total daily concrete material consumption of the concrete mixing station, calculate the corresponding concrete material consumption in each time period according to a fixed time cycle, and compare it with the concrete material inventory balance of the mixing station in the corresponding time period to obtain the comparison results of concrete material consumption and balance; Different concrete material inventory balance status labels are assigned to the concrete material consumption and balance comparison results in each time period. The status labels include sufficient, critical, and shortage. All status labels are integrated to obtain a status label sequence.

3. The information-based concrete mixing station management system according to claim 1 is characterized in that: The steps for obtaining the inventory change forecast result are specifically as follows: Extracting state tag pairs of adjacent time periods in the state tag sequence, comparing the state tag contents of the state tag pairs of adjacent time periods, determining whether the state has changed, counting the transition frequencies of each state change in all time periods, and constructing a state tag transition frequency table; Initializing a Markov chain model, inputting the state label transfer frequency table into the Markov chain model, and constructing a corresponding state label transfer probability matrix to predict the transfer probability of the state label of the current concrete material inventory balance to the state labels of other concrete material inventory balances in multiple future time periods, thereby obtaining a future transfer probability prediction result; According to the future transfer probability prediction result, a future change path of the concrete material inventory balance is identified. The future change path includes a continuous shortage of the concrete material inventory balance, a rebound to a critical state, and a gradual recovery to a sufficient state, thereby obtaining an inventory change prediction result.

4. The information-based concrete mixing station management system according to claim 1 is characterized in that: The steps for obtaining the potential energy distribution diagram of the conveyor belt are specifically as follows: Obtaining and normalizing the conveyor belt operating parameters of the mixing station, wherein the conveyor belt operating parameters include the conveyor belt tension, belt speed, and motor load, and obtaining the processed conveyor belt operating parameters; The processed conveyor belt operating parameters of each time period are respectively combined into corresponding vector forms and mapped to the potential energy space in chronological order. In the potential energy space, the conveyor belt operating parameters represent the conveyor belt operating status points in each time period, and a conveyor belt potential energy distribution diagram is constructed.

5. The information-based concrete mixing station management system according to claim 4 is characterized in that: The steps for obtaining the conveyor belt control result are specifically as follows: Based on the conveyor belt potential energy distribution map, the conveyor belt running state point is divided into multiple local neighborhoods according to the distance in the potential energy space according to the comparison result, and the local neighborhood division result is obtained; Based on the local neighborhood division results, the local potential energy density of each conveyor belt operation status point in its corresponding local neighborhood is calculated, the aggregation degree and density gradient change of each conveyor belt operation status point are analyzed according to the local potential energy density, and the corresponding density area boundaries are divided; Obtain the position of the conveyor belt operating parameters in the potential energy space, calculate the spatial position offset between consecutive time periods, determine the offset trajectory based on the spatial position offset, compare the offset trajectory with the density area boundary, and use the comparison result to identify whether the conveyor belt operating status is migrating towards a blocking trend, thereby obtaining the conveyor belt operating status analysis result; Combined with the conveyor belt operation status analysis result and the future change path of the concrete material inventory balance in the inventory change prediction result, the conveyor belt operation mode is adjusted with reference to the conveyor belt operation status and the future inventory balance to obtain the conveyor belt control result.

6. The information-based concrete mixing station management system according to claim 1 is characterized in that: The steps for obtaining the Boolean state sequence are specifically as follows: Based on the conveyor belt control result, the opening and closing signals of the mixing station feed port after the conveyor belt is adjusted are collected in real time, and the opening and closing signals are counted according to the number of switching of the opening and closing actions within a specified time. By setting an opening and closing frequency threshold, the time period in which the number of opening and closing switching exceeds the opening and closing frequency threshold is divided into an abnormal closing time period, and the switching number statistics result is obtained; Based on the statistical results of the switching times, the discharge response detection is performed on the time period that remains in the open state, and the time period when the material does not flow or the sensor continuously feeds back the blocking signal is divided into the abnormal blocking time period. The Boolean state marks of abnormal closure, abnormal blocking and corresponding normal operation are set to construct the Boolean state sequence during the operation of the feed port.

7. The information-based concrete mixing station management system according to claim 1 is characterized in that: The steps for obtaining the feed port blocking state warning signal are specifically as follows: Based on all the collected opening and closing signals, the Boolean difference method is used to compare the differences between the Boolean state sequences in the past and the current operation stages, and the frequency of Boolean state transitions newly added to the Boolean state sequence in the current operation stage compared with the Boolean state sequence in the historical operation stage is calculated to identify whether the material blocking phenomenon shows an abnormally increasing trend; From the statistical frequency of the Boolean state transitions, the section where the abnormal strengthening trend first appears is extracted as the initial point of the material blockage anomaly. The duration and time interval distribution of the subsequent abnormal strengthening trend are statistically analyzed to determine whether the material blockage state is an instantaneous fluctuation or a continuous anomaly. An early warning signal for the material blockage state at the feed port is generated for intervention management of the feeding link of the concrete mixing station.

Images