JP6851247B2 - Operation planning device, operation control system, and operation planning method - Google Patents

Description

The present invention relates to an operation planning device, an operation control system, and an operation planning method. Specifically, a technique capable of formulating an operation plan that appropriately reflects the situation and operation know-how of each plant. Regarding.

When operating various plants such as water and sewage facilities, formulate an operation plan to optimize the quality and efficiency of operation while considering various conditions such as the specifications of the facility, the supply-demand relationship of products, and operating resources. There is a need.

As a conventional technique related to such an operation plan, for example, in a plant operation control device that controls control of plant equipment in a plant based on an operation plan created in advance, process data input from the plant via a process controller is input. A demand forecasting unit that predicts and calculates demand based on a process data storage means to be stored, past actual values stored in the process data storage means, and predetermined information input from a human interface, and the demand forecasting unit. When the IA optimal plan calculation means that performs a calculation on the optimum operation plan using an immune algorithm based on the predicted demand value calculated and the IA optimal plan calculation means performs a calculation using the immune algorithm. , A plant operation control device (see Patent Document 1), and the like, which are provided with a cell storage means for storing memory cells and suppressor cells, and the like have been proposed.

Japanese Unexamined Patent Publication No. 2003-228402

In the prior art, it is possible to obtain a semi-optimal operation plan at high speed by using the actual value as the initial solution of optimization. However, as the target, we do not assume a plant with a wide variety of facilities such as distribution reservoirs and pumps, and the operation tendency of skilled operators who should be latent in the operation results is appropriately applied to the operation plan. It will not be reflected. In other words, from the viewpoint of optimizing the operation plan, there remains the problem that the events that should be reflected in the operation plan are not sufficiently reflected. These issues are particularly clear in the water system, which has problems such as difficulty in maintaining the business due to future population decline, aging of skilled workers, and unsuccession of driving know-how due to retirement.

Therefore, an object of the present invention is to provide a technique capable of formulating an operation plan that appropriately reflects the situation of each plant and the operation know-how.

The operation planning device of the present invention that solves the above problems is a device that plans an operation plan of a plant, extracts the distribution of the operation range related to a predetermined event from the operation record data related to the plant, and deviates from the operation range. By combining the operation range extraction unit that determines the basic index indicating the degree for each predetermined event and the basic index of the predetermined event, an evaluation index in the operation plan is generated, and the constraint conditions related to the configuration of the plant and the evaluation index are generated. By solving the optimization problem with the objective function, an operation plan is drafted for a predetermined period in the past, the degree of agreement between the operation plan and the operation record data for the period is calculated, and the degree of agreement is set to the maximum. The constraint condition to be satisfied in the operation plan is calculated from the problem configuration learning unit for searching the configuration of the evaluation index, the predetermined demand forecast value for the plant, and the latest operation record data for the plant, and the constraint condition and the above It is characterized by having an operation plan planning unit that formulates an operation plan by solving an optimization problem using the searched evaluation index as an objective function.

Further, the operation control system of the present invention is an operation control system that controls a plant based on an operation plan, and is a monitoring control that collects measured values by a sensor of the plant and gives a control instruction to a sub-controller that controls the plant. It is an operation plan planning device that formulates an operation plan that is a control target of the device and the monitoring and control device, and is an operation range related to a predetermined event from operation record data that is a measured value for the plant obtained through the monitoring and control device. By extracting the distribution of the above and combining the operation range extraction unit that determines the basic index indicating the degree of deviation from the operation range for each predetermined event and the basic index of the predetermined event, an evaluation index in the operation plan is generated. By solving the constraint conditions related to the configuration of the plant and the optimization problem using the evaluation index as the objective function, an operation plan is drafted for a predetermined period in the past, and the operation plan and the operation record data for the period are combined. The operation plan is satisfied from the problem configuration learning unit that calculates the degree of agreement and searches for the configuration of the evaluation index that maximizes the degree of agreement, the predetermined demand forecast value for the plant, and the latest operation record data for the plant. Includes an operation plan planning device including an operation plan planning unit that calculates an operation plan to be calculated and solves an optimization problem using the constraint condition and the searched evaluation index as an objective function. It is characterized by.

Further, in the operation planning method of the present invention, the information processing apparatus for planning the operation plan of the plant extracts the distribution of the operation range related to a predetermined event from the operation record data related to the plant, and indicates the degree of deviation from the operation range. By combining the operation range extraction process in which the basic index is determined for each predetermined event and the basic index of the predetermined event, the evaluation index in the operation plan is generated, and the constraint conditions related to the configuration of the plant and the evaluation index are used as the objective function. By solving the optimization problem, an operation plan is drafted for a predetermined period in the past, the degree of agreement between the operation plan and the operation record data for the period is calculated, and the evaluation that maximizes the degree of agreement. The constraint conditions to be satisfied in the operation plan are calculated from the problem configuration learning process for searching the index configuration, the predetermined demand forecast value for the plant, and the latest operation record data for the plant, and the constraint conditions and the searched evaluation are calculated. It is characterized by executing an operation plan planning process that formulates an operation plan by solving an optimization problem using an index as an objective function.

According to the present invention, it is possible to formulate an operation plan that appropriately reflects the situation of each plant and the operation know-how.

It is a figure which shows the logical configuration example of the operation control system in Example 1. FIG. It is a figure which shows the hardware configuration example of the operation planning apparatus in Example 1. FIG. It is a figure which shows the composition example of the water supply facility group which is the operation control target in Example 1. FIG. It is a figure which shows the example of the operation plan in Example 1. FIG. It is a figure which shows the example of the operation plan in Example 1. FIG. It is a figure which shows the example of the distribution of the operation record and the basic index value in Example 1. FIG. It is a figure which shows the flow example of the operation plan planning method in Example 1. FIG. It is a figure which shows the example of the problem structure display window in Example 1. FIG. It is a figure which shows the example of the operation plan display window in Example 1. FIG. It is a figure which shows the logical configuration example of the operation control system in Example 2. FIG. It is a figure which shows the flow example of the operation plan planning method in Example 2. It is a figure which shows the example of the problem composition display window by operation condition in Example 2. FIG.

−−− Example 1−−−
Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings. FIG. 1 is a diagram showing a logical configuration example of the operation control system 100 including the operation planning device 101 in the first embodiment. The operation control system 100 in this embodiment is a system that controls each device in a water supply plant based on an operation plan planned in advance by the operation plan planning device 101 and manages the transfer / distribution process of the water supply plant. In this embodiment, the target of operation planning and operation control is a water supply plant, but of course, it is not limited to this.

As illustrated in FIG. 1, the operation control system 100 in this embodiment includes an operation planning device 101, a monitoring control device 102, a sensor 103, and a sub controller 104.

Of these, the operation plan planning device 101 includes an operation range extraction unit 111, a problem configuration learning unit 112, a demand forecast unit 113, an operation plan planning unit 114, an operation record data storage unit 121, a data collection unit 151, a plan output unit 152, and , Configuration / plan display unit 153.

The above-mentioned operation range extraction unit 111 acquires past operation record data related to the relevant water plant from the operation record data storage unit 121, extracts the distribution of the operation range related to a predetermined event from the operation record data, and extracts the operation range from the operation record data. A basic index indicating the degree of deviation from the above is determined for each of the above-mentioned predetermined events. Further, the operation range extraction unit 111 transmits information regarding the basic index determined as described above to the problem configuration learning unit 112 and the configuration / plan display unit 153. The details of the processing of the operation range extraction unit 111 will be described later together with the description of FIG.

Further, the problem configuration learning unit 112 is operated by acquiring past operation record data related to the relevant water plant from the operation record data storage unit 121 and combining the basic indexes obtained from the above-mentioned operation range extraction unit 111. By generating the evaluation index of the plan, solving the optimization problem with the constraint conditions related to the configuration of the water plant and the above evaluation index as the objective function, an operation plan is drafted for the past predetermined period, and this operation plan and this The degree of agreement with the operation record data for the relevant period is calculated, and the configuration of the evaluation index having the maximum degree of agreement is searched for. Further, the problem composition learning unit 112 transmits the configuration of the evaluation index having the maximum degree of coincidence thus obtained as a problem configuration to the operation plan planning unit 114 and the configuration / plan display unit 153. The details of the processing of the problem structure learning unit 112 will be described later together with the explanation of FIG.

Further, the demand forecast unit 113 acquires the past operation record data related to the relevant water plant from the operation record data storage unit 121, calculates the forecast value of the demand based on the operation record data, and calculates the forecast value of the demand. Is transmitted to the operation planning unit 114. Here, the predicted value of demand is the predicted value of the amount of water distributed for each water distribution area in the water supply plant for each predetermined time step (for example, about 30 minutes) in a predetermined future period (for example, for 24 hours) from the time of prediction. Refers to the time series. A known time-series forecasting method is adopted as the calculation method of such a demand forecast.

In addition, the operation planning unit 114 acquires the latest operation record data related to the relevant water plant from the operation record data storage unit 121, acquires the above-mentioned problem configuration obtained from the problem composition learning unit 112, and also obtains the demand forecast. The forecast value of demand was acquired from the unit 113, the constraint condition to be satisfied in the operation plan was calculated from the demand forecast value and the latest operation record data, and this constraint condition and the above-mentioned problem configuration learning unit 112 were calculated. An operation plan is formulated by solving an optimization problem with the evaluation index as the objective function. Further, the operation plan planning unit 114 transmits the drafted operation plan to the plan output unit 152 and the configuration / plan display unit 153. The details of the processing of the operation planning unit 114 will be described later together with the explanation of FIG. The details of the operation plan will be described later in the description of FIG.

Further, the operation record data storage unit 121 acquires the operation record data of the transfer / distribution process targeted for the operation plan in the water supply plant from the data collection unit 151, accumulates the operation record data, and stores the operation record data in response to the request. The data is transmitted to the operation range extraction unit 111, the problem configuration learning unit 112, the demand forecast unit 113, and the operation planning unit 114.

The operation record data refers to the sensor measurement value of the water supply / delivery process in the water supply plant, the data of the failure state of the equipment and the sensor, and the like. Further, the operation record data may include related data managed by the monitoring control device 102, that is, alarm information regarding changes in the failure state of the device or sensor.

Further, the data collecting unit 151 receives the operation record data of the transfer / distribution process of the operation plan target in the water supply plant from the monitoring control device 102, and transmits the operation record data to the operation record data storage unit 121. It is assumed that the data collection unit 151 and the monitoring control device 102 are communicable via an appropriate network.

Further, the plan output unit 152 acquires an operation plan from the operation plan planning unit 114 and transmits the operation plan to the monitoring control device 102 as a target value for operation control.

Further, the configuration / plan display unit 153 acquires information on the distribution of the operation range and the basic index from the operation range extraction unit 111, acquires the problem configuration from the problem composition learning unit 112, and also acquires the problem configuration from the operation plan planning unit 114. An operation plan is acquired, and the acquired information is displayed in a window on a display for an appropriate operator such as a display unit 206, which will be described later. A display example of such a configuration / plan display unit 153 will be described later as a description of FIGS. 7 and 8.

Further, the monitoring control device 102 collects measured values from a sensor 103 that measures the state of the water supply / distribution process in the water supply plant subject to operation control, and the measured values and the failure state of the sensor 103 and the equipment in the water supply plant. It is a device that transmits information and alarm information regarding changes in the failure state of the sensor 103 and the device to the operation planning device 101. Further, the monitoring control device 102 receives an operation plan from the operation plan planning device 101 as a target value of the operation control, and controls the state of the transmission / distribution process in the water plant subject to the operation control based on the operation plan. The control target value is transmitted to the controller 104.

The operation planning device 101 may be realized as a program on a data center installed at a remote location from the monitoring control device 102. Further, the operation planning device 101 may be divided into a program on a data center in a remote location and a terminal placed on the side of the monitoring control device 102. For example, an operation range extraction unit 111 and a problem configuration learning unit 112 can be implemented in a program on a data center, and a portion other than the operation range extraction unit 111 and the problem configuration learning unit 112 can be implemented in the above-mentioned terminal.

Subsequently, the hardware configuration of the operation planning device 101 in this embodiment will be described. FIG. 2 is a diagram showing a hardware configuration example of the operation planning device according to the first embodiment.

As illustrated in FIG. 2, the operation planning device 101 in this embodiment includes a CPU 201, a memory 202, a media input / output unit 203, an input unit 205, a communication control unit 204, a display unit 206, a peripheral device IF unit 207, and a peripheral device IF unit 207. , Bus 210, and so on.

Of these, the CPU 201 is an arithmetic unit that executes the program 2021 on the memory 202. Further, the memory 202 is a storage means for temporarily storing the above-mentioned program 2021 and tables. Further, the media input / output unit 203 holds the above-mentioned programs 2021 and tables read from a predetermined storage medium, and appropriately stores them in the memory 202.

Further, the input unit 205 is a device that provides the user with an input interface such as a keyboard and a mouse. Further, the communication control unit 204 is a network interface or the like that connects to the network 220 and executes communication with an external device such as the monitoring control device 102.

Further, the display unit 206 is a device that is a display destination of information by the configuration / plan display unit 153 of FIG. 1, and is specifically a display. Further, the peripheral device IF unit 207 is an interface for a printer or the like.

The bus 210 interconnects the CPU 201, the memory 202, the media input / output unit 203, the input unit 205, the communication control unit 204, the display unit 206, and the peripheral device IF unit 207.

As is clear from the comparison between FIGS. 1 and 2, the operation planning device 101 of FIG. 1 is realized by the CPU 201 executing the program 2021. The operation planning device 101 and the monitoring control device 102 may be realized as different programs on the same hardware.

FIG. 3 is a diagram showing a facility configuration of a water transmission / distribution system in a water supply plant subject to operation control in the first embodiment. With reference to FIG. 3, a configuration of a water supply transfer / distribution process, which is a water supply plant monitored by the operation planning device 101, will be described.

In the equipment configuration illustrated in FIG. 3, water is pumped from the distribution reservoirs 301 and 302 to the distribution area 341 by the distribution pump facilities 321 and 322 by multipoint injection. In the figure, only typical water pipes such as water pipe 354 are shown.

Further, in the above-mentioned water distribution area 341, there are terminal stations 361 and 361, where water pressure and water quality are measured. In addition, water is naturally flowed from the distribution reservoir 303 to the distribution area 342 through a pressure reducing valve 334. On the other hand, the inflow to the distribution reservoir 301 consists of receiving water from the water supply company through the water pipe 351 and purifying the raw water from the intake pump facility 324 at the water purification plant 311. A part of the water in the distribution reservoir 301 is sent to the distribution reservoir 303 via the water supply pump facility 323 and the water pipe 353. Further, the inflow to the distribution reservoir 322 is the reception of water from the water supply company through the water pipe 352. The flow rate adjusting valves 331, 332, and 333 are arranged at the inflow portion from the water pipe of each distribution reservoir.

In this example, the sensor 103 for which the monitoring control device 102 collects the measured values is the water level gauge of each distribution reservoir, each pump facility, the flow meter at the valve, the water pressure gauge at each pump facility and the terminal station, and the pump of each pump facility. The operating unit, the number of revolutions, the measuring instrument of power consumption, the measuring instrument of the opening degree of each valve, etc. are applicable.

Further, in this example, the sub-controller 104 to which the monitoring control device 102 instructs the control corresponds to a controller that controls the start / stop of each pump, the rotation speed adjusting device, the opening degree adjustment of each valve, and the like.

Subsequently, an operation plan example in the first embodiment will be described with reference to FIGS. 4A and 4B. Here, the operation plan refers to a plan for transition of a control target or a process state in a predetermined future period (for example, for 24 hours) from the time of making the operation plan. Specific examples of such control targets or process states include the water level of the distribution reservoir, the amount of water taken in and distributed by each flow meter, the number of pumps operated in each pump facility, the number of revolutions, the opening degree of each valve, and the like.

FIG. 4A shows the transition 400 of the water level of the distribution reservoir A as an example of the operation plan, and FIG. 4B shows the transition 410 of the number of pumps in the water supply pump facility S as an example of the operation plan.

The transition in such an operation plan is expressed in a time series of values for each time step (hereinafter, 30 minutes as an example). At this time, in order to express the process that changes from moment to moment with a value every 30 minutes, a value representing a time step is determined by an appropriate aggregation method. For example, the water level is the value at 0 and 30 minutes per hour, and the water intake, water supply, and distribution amount are the average values for each 30 minutes. If the target has no margin in the capacity of the distribution reservoir facility, etc., it is necessary to enable the number of pumps to be operated not only at 0 and 30 minutes per hour but also at any time.

Next, with reference to FIG. 5, an example of the distribution of the operating range and the basic index extracted by the operating range extracting unit 111 of this embodiment will be described.

The operation range extraction unit 111 in this embodiment acquires operation record data from the operation record data storage unit 121, and based on this, performs processing in each step of extracting the operation range, defining the basic index, and transmitting the result.

Of these, in the operation record data acquisition step, the operation range extraction unit 111 acquires the operation record data from the operation record data storage unit 121.

Further, in the operation range extraction step, the operation range extraction unit 111 calculates a typical operation range of the operation record data for each target item. The item to be processed by the operation range extraction unit 111, that is, the target item is a preset measurement value of the process state. For example, the operation range extraction unit 111 targets events such as water intake amount, water supply amount, water distribution amount, distribution reservoir water level, number of operation switching operations of various pumps and valves, interval, time zone, and operation time.

Further, the operation range extraction unit 111 can extract the distribution of a plurality of operation ranges and determine the basic index by using a plurality of time divisions and aggregation methods for the same measured value. For example, the operation range extraction unit 111 can extract the operation range of the 30-minute average value and the operation range of the integrated value per day for the amount of water intake, and set different basic indexes for each.

Further, the operation range extraction unit 111 may extract the distribution of the operation range from the processed value of the measured value and determine the basic index. For example, the operation range extraction unit 111 determines the amount of change in the amount of water sent from the previous time, the power consumption required for operating the water supply / distribution pump, and the 30-minute average value (power demand value) of the power in each facility based on the power consumption. , The index of the robustness of the operation plan against the error of the demand forecast can be processed.

As for the robustness of the operation plan against the error of the demand forecast, for example, in the situation where the demand amount is continuously higher or lower than the forecast, the transition of the distribution reservoir water level when the operation operation according to the operation plan is continued is simulated. However, the maximum magnitude at which the distribution reservoir water level deviates from the operating range within a predetermined time can be used.

For example, the operation range extraction unit 111 sets the number of times of switching of the number of pumps per day in a certain water distribution pump facility as a target item, calculates a histogram of the item, and calculates a range including most of the actual data.

The distribution graph 500 of (a) operation results shown in FIG. 5 is a histogram of the number of times of switching of the number of pumps per day in a certain water distribution pump facility calculated by the operation range extraction unit 111. The operation range extraction unit 111 calculates the range of the item by calculating the upper limit value of the number of switching times in which the relative frequency is equal to or higher than a predetermined value. The upper limit of the calculated range of the operation range extraction unit 111 is shown by a broken line in the figure.

As the method of calculating the range by the operation range extraction unit 111, a method of calculating a predetermined percentile value according to a target item or the like, a method of calculating a value obtained by a predetermined multiple of the standard deviation from the average value, or the like is used. In addition, not only the upper limit value but also the lower limit value is calculated according to the target item and the like. If necessary, a plurality of upper limit values and lower limit values may be calculated for one target item.

Further, the operation range extraction unit 111 determines a calculation method of the basic index for quantifying the degree of deviation from the above-mentioned operation range in the basic index definition step. For example, the operation range extraction unit 111 defines the following calculation method as a basic index for the above-mentioned pump switching number using the operation range (switching number upper limit value).

(Basic index value) = max [(Switching count)-(Switching count upper limit), 0]
Here, max is the maximum value operation.

(B) The basic index value graph 510 in FIG. 5 is a basic index value of the number of times of switching of the number of pumps per day in a certain water distribution pump facility, which is defined by the operation range extraction unit 111 by the method as described above.

Further, the operation range extraction unit 111 transmits the above-mentioned list of basic indexes and their calculation methods to the problem configuration learning unit 112, and ends the process.

The operation planning device 101 can extract the operation tendency of the (experienced) operator for each operation range extraction item based on the past operation record data by the processing of the operation range extraction unit 111 described above. The operation plan planning device 101 can formulate an operation plan capable of continuing stable operation even if an error occurs in the demand forecast by using the robustness of the operation plan with respect to the error of the demand forecast as a basic index.

Hereinafter, the actual procedure of the operation planning method in the present embodiment will be described with reference to the figure. Various operations corresponding to the operation planning method described below are realized by a program read by the operation planning device 101 into a memory or the like and executed. Then, this program is composed of the code for performing various operations described below.

FIG. 6 is a diagram showing a flow example of the operation planning method in the first embodiment, and specifically, is a flowchart showing a processing flow of the problem configuration learning unit 112. Hereinafter, the processing of the problem structure learning unit 112 will be described with reference to the flow of FIG.

In this case, first, the problem structure learning unit 112 starts the process (step 601). This start is executed by receiving a predetermined instruction from a predetermined device via the input unit 205 or the communication control unit 204, or by detecting the arrival of a predetermined time.

Subsequently, the problem configuration learning unit 112 acquires operation record data from the operation record data storage unit 121, and also acquires a list of basic indicators and their calculation methods from the operation range extraction unit 111 (step 602).

Further, the problem structure learning unit 112 generates an evaluation index of the operation plan by combining the basic indexes obtained in the above-mentioned step 602 (step 603). The problem structure learning unit 112 in this step generates at least one evaluation index by randomly combining basic indexes by, for example, a linear operation and a maximum value calculation.

If the vector expressing the operation plan is X, the plant state up to the time of the operation plan is s, and the basic index or the index combining the basic indexes is h_i (where _ is an abbreviation for the subscript), it is linear. As an example of an index that can be composed of a combination of calculation and maximum value calculation

がある。ここで、ｗ＿ｉ、ｋ＿ｉは任意の定数である。

There is. Here, w_i and k_i are arbitrary constants.

Next, the problem composition learning unit 112 formulates an operation plan for a predetermined period in the past by solving an optimization problem using the above-mentioned constraints on the configuration of the water supply plant and the evaluation index obtained in step 603 as the objective function. (Step 604).

In this case, the problem composition learning unit 112 sets the evaluation index obtained in step 603 as f, and sets a plurality of constraint conditions regarding the configuration of the water supply plant as g_j (j = 1, 2, ..., N), and sets the operation record data. For a certain past period p, if the vector representing the state of the plant affecting the period is s_p, the optimization problem

を解いて最適な運用計画案Ｘ＊＿ｐを立案する。

To formulate the optimal operation plan X * _p.

Specifically, the above-mentioned state s_p includes the amount of demand (actual value or predicted value) in the period p, the water level of the distribution reservoir immediately before the period, the number of pumps in operation, and the total amount of water intake before the period. Values etc. are included.

In addition, as examples of constraints on the configuration of water supply plants, secure the amount of water distribution that satisfies the water demand, the amount of water to be taken and distributed is within the design range of each facility, and the water level of the distribution reservoir is within the design range of the facility. That is, the relational expression of the water volume balance is satisfied between the intake and distribution amount and the distribution reservoir water level. As a method for formulating these constraints, a known technique for formulating an operation plan for transportation and distribution can be used.

Further, as a method of obtaining an operation plan as an optimum solution of an optimization problem, for example, a known technique such as a genetic algorithm or a mathematical programming method can be used.

The problem structure learning unit 112 prepares a plurality of periods p for evaluation in the next step, and formulates an operation plan for each period.

Subsequently, the problem composition learning unit 112 calculates the degree of agreement between the operation plan draft drafted in step 604 described above and the operation record data in the period, and searches for the configuration of the evaluation index having the maximum degree of agreement. (Step 605).

The problem composition learning unit 112 in this step evaluates the operation plan drafted by using the evaluation index f as the objective function, for example, by the degree of agreement given by the following equation.

ここで、Ｅ［ｆ］は評価値、ａ＿ｐは期間ｐにおける運用計画案Ｘ＊＿ｐに対応した実績値，［・］＿ｍはベクトルの第ｍ成分、ｌ＿ｍ，αは定数である。

Here, E [f] is an evaluation value, a_p is an actual value corresponding to the operation plan draft X * _p in the period p, [・] _m is the mth component of the vector, and l_m and α are constants.

The above-mentioned equation of the degree of agreement is calculated based on the water intake amount, the water supply amount, the water distribution amount, the distribution reservoir water level, and the operation switching time of the pump and the valve by the setting method of the constant l_m.

Subsequently, the problem structure learning unit 112 processes the problem structure on the assumption that the evaluation index f having a sufficiently large degree of coincidence is obtained based on the degree of coincidence E [f] calculated for the evaluation index f configured so far. It is determined whether or not to end (step 606).

As a result of the above determination, when the process ends (step 606: end), the problem structure learning unit 112 shifts the process to step 607. On the other hand, as a result of the above determination, when continuing (step 606: continuation), the problem structure learning unit 112 returns the process to step 603.

As a specific method for determining the end of processing in step 606 and a method for constructing an evaluation index in step 603, a known technique such as genetic programming can be used.

Next, the problem composition learning unit 112 selects the evaluation index having the maximum degree of agreement from the evaluation indexes configured so far, and sets the evaluation index selected as the objective function and the above-mentioned constraint condition regarding the configuration of the water supply plant. A set is defined as a problem configuration, the problem configuration is transmitted to the operation plan planning unit 114 and the configuration / plan display unit 153 (step 607), and the flow ends (step 608).

The operation planning device 101 determines the overall requirements and judgments of the operators regarding each operation range extraction item that may have a trade-off relationship with each other by the processing of the problem configuration learning unit 112 described above, and prioritizes each item. As a side note, it can be extracted based on past operation record data.

In addition, the operation plan planning unit 114 performs an operation plan planning process based on the problem structure received from the problem structure learning unit 112 for a predetermined future period from the time of plan planning, targeting the plan planning target period. The formulation of the optimization problem and the algorithm for solving the optimization problem are the same as the processing in step 604 of the problem structure learning unit 112.

Further, the operation planning device 101 is processed by the operation planning unit 114 described above, so that the operation range extraction unit 111 may have any combination of the planned initial water level of the distribution reservoir, the planned initial operation number of the pump facility, and the like. And, it is possible to formulate an operation plan that reflects the past demands and judgments of the (experienced) operator extracted by the problem structure learning unit 112.

The operation range extraction unit 111 and the problem configuration learning unit 112 perform the processing at a predetermined cycle, for example, every few months. In addition, the operation planning unit 114, in principle, has a 24-hour or 12-hour cycle, and performs the processing in response to an instruction from the operator according to the degree of dissociation from the plant operating state. Further, during the period between the processing cycles of the operation range extraction unit 111 and the problem configuration learning unit 112, the operation planning unit 114 draws an operation plan using the problem configuration finally calculated by the problem configuration learning unit 112.

Note that FIG. 7 is a diagram showing an example of the problem configuration display window 701. With reference to FIG. 7, the form of the problem configuration displayed by the configuration / plan display unit 153 on the display unit 206 and the like will be described.

The problem configuration display window 701 displayed by the configuration / plan display unit 153 on the display unit 206 such as a display has an objective function display panel 711. The configuration / plan display unit 153 displays the configuration of the objective function (evaluation index) among the problem configurations obtained from the question configuration learning unit 112 on the objective function display panel 711.

The objective function display panel 711 shows an example when an evaluation index determined by linear calculation of the basic index, that is, equation (2) is selected as the objective function. Columns 721 to 723 show the items of the basic index, and column 724 shows the threshold value of the item (the boundary value of the range calculated by the operation range extraction unit 111). The product of the reciprocal of column 725 and column 726 is the coefficient w_i with respect to the corresponding basic index h_i in equation (2).

Further, the configuration / plan display unit 153 may accept the modification of parameters such as the threshold value and the weight as an input in the objective function display panel 711. When the modification is accepted, the configuration / plan display unit 153 transmits the modified parameter to the operation planning unit 114. On the other hand, the operation planning device 101 presents the extracted (experienced) operator's past requests and judgments to the operator by the processing in the configuration / plan display unit 153 described above, and if necessary. Corrections can be accepted.

Further, FIG. 8 is a diagram showing an example of the operation plan display window 801. With reference to FIG. 8, a mode in which the configuration / plan display unit 153 presents the evaluation results regarding the operation plan and its basic index to the operator on the display unit 206 and the like will be described.

The operation plan display window 801 that the configuration / plan display unit 153 displays on the display unit 206 such as a display in this case includes an item selection panel 811, an index value display panel 812, and a plan detail display panel 813.

The configuration / plan display unit 153 displays the options of the operation plan and the basic index items to be displayed on the item selection panel 811 among the above-mentioned panels. Further, the configuration / plan display unit 153 receives the selection operation from the operator on the item selection panel 811 and receives the input of the operation plan and the basic index items to be displayed.

Further, the configuration / plan display unit 153 positions the operation plan in the distribution of the operation range extracted by the operation range extraction unit 111 for the items selected by the item selection panel 811 with respect to the index value display panel 812. Display and calculate and display the corresponding basic indicators.

Further, the configuration / plan display unit 153 graphs the index function 821 and the threshold value 822 received from the operation range extraction unit 111 on the index value display panel 812, and superimposes the plan value 825 on the index value 826. Is visualized, and the degree of deviation 827 from the operating range is displayed numerically.

The configuration / plan display unit 153 displays the transition of the items selected in the item selection panel 811 among the operation plans received from the configuration / plan display unit 153 in time series with respect to the plan detail display panel 813 in the planning period. The graph is displayed as a planned value time series 835. Further, the configuration / plan display unit 153 displays the threshold value 831 in an overlapping manner.

The operation plan planning device 101 evaluates the drafted operation plan from the viewpoint of the satisfaction (deviation degree) of the operator's past requests and judgments extracted by the processing of the configuration / plan display unit 153 described above, and the operator. Can be presented to.

--- Example 2---
In this embodiment, an example is shown in which the operation planning device 101 includes an operation condition extraction unit 915 that extracts the operation conditions of the plant based on the equipment state of the monitoring control system 102 in addition to the configuration of the first embodiment.

In this case, the operation planning unit 101 searches for and calculates changes to be added to the composition of the evaluation index for each operation condition by the problem configuration learning unit 112, and the operation planning unit 114 calculates the evaluation index corresponding to the operation condition. The configuration will be selected as the objective function. Since most of the configurations and processes in the operation planning apparatus 101 are the same as those in the first embodiment, the duplicate description will not be repeated and only the differences will be described.

FIG. 9 is a diagram showing a logical configuration of the operation plan planning device 101 in the second embodiment. Specifically, FIG. 9 is a configuration example of the operation control system 100 including the operation plan planning device 101 including the operation condition extraction unit 915. It is a figure which shows.

The operation condition extraction unit 915 in this embodiment acquires the operation record data from the operation record data storage unit 121, extracts the difference from the normal time of the equipment state in the water supply plant from the operation record data, and extracts this as the operation condition. The operation conditions are transmitted to the problem composition learning unit 112 and the operation planning unit 114.

For example, if the operation record data includes information that the equipment of a specific distribution reservoir and distribution pump facility has temporarily lost power due to an electrical inspection or the like during a certain period, the operation condition extraction unit 915 may use this distribution reservoir. And the power outage in the water distribution pump facility is extracted as one operating condition. The operating conditions extracted by the operating condition extraction unit 915 are not limited to power outages, but include malfunctions and suspension of use of mechanical equipment such as pumps, malfunctions of instrumentation equipment such as flow meters, and partial functional restrictions of monitoring and control systems. Including.

The problem configuration learning unit 112 in this embodiment additionally receives the operation conditions from the above-mentioned operation condition extraction unit 915, learns the problem configuration for the normal conditions and each operation condition, and sets the problem configuration to the operation planning unit 114 and the configuration. -Send to the plan display unit 153. The details of the problem configuration learning unit 112 of this embodiment will be described later in the description of FIG.

The operation planning unit 114 of this embodiment additionally receives the operation conditions in the planning target period from the operation condition extraction unit 915, and the problem configuration learning unit 112 from the problem composition learning unit 112, particularly the problem configuration corresponding to the operation conditions, particularly the objective function. The configuration of the evaluation index to be used is received, an operation plan is formulated using the problem configuration corresponding to the operation conditions, and the operation plan is transmitted to the plan output unit 152 and the configuration / plan display unit 153.

FIG. 10 is a diagram showing a flow example of the operation plan planning method in this embodiment, and specifically, is a flowchart showing the processing of the problem configuration learning unit 112. Hereinafter, the processing of the problem configuration learning unit 112 in this embodiment will be described with reference to FIG.

First, the problem structure learning unit 112 starts processing (step 1001). This start is executed by receiving a predetermined instruction from a predetermined device via the input unit 205 or the communication control unit 204, or by detecting the arrival of a predetermined time.

Next, the problem configuration learning unit 112 operates the operation record data from the operation record data storage unit 121, the list of basic indicators and their calculation methods from the operation range extraction unit 111, and the past operation from the operation condition extraction unit 915. Each condition is received (step 1002).

Next, the problem configuration learning unit 112 learns the problem configuration under normal conditions, that is, the most typical and long-running operating conditions under the same conditions (step 1003). In this step, the target period p of learning is limited to the period under normal conditions, and the processes from step 603 to step 606 in FIG. 6 are performed.

Next, the problem configuration learning unit 112 learns the problem configuration for each operation condition other than the normal condition (step 1004). In this step, the target period p of learning is limited to the period under each operating condition, and the configuration of the evaluation index is limited to the configuration close to the index under normal conditions, and steps from step 603 in FIG. 6 are performed. Process up to 606.

It should be noted that the configuration of the above-mentioned evaluation index is close to the index of the normal condition, for example, the vector of the constants (w_i and k_i in the equations (1) and (2)) that determine the evaluation index of the operation condition. And the distance from the constant vector that determines the evaluation index under normal conditions is smaller than the predetermined value. For the distance between the vectors, the L1 norm and L2 norm of the difference between the two vectors, the number of different elements, and the like can be used.

Next, the problem configuration learning unit 112 transmits the normal conditions and the problem configurations for each operation condition obtained in steps 1003 and 1004 described above to the operation plan planning unit 114 and the configuration / plan display unit 153 (step 1005). ), End the flow (step 1006).

The operation plan planning device 101 of this embodiment has an operation condition in which the equipment state in the water supply plant is special due to the additional processing in the operation condition extraction unit 915, the problem configuration learning unit 112, and the operation plan planning unit 114 described above. It is possible to extract changes in the operator's past demands and judgments regarding operation, and to formulate an operation plan according to the equipment status.

FIG. 11 is a diagram showing an example of the problem configuration display window 1101 according to operating conditions. A mode in which the configuration / plan display unit 153 presents the problem configuration for each operating condition to the operator will be described with reference to FIG.

The operation condition-specific problem configuration display window 1101 displayed by the configuration / plan display unit 153 on the display unit 206 such as a display includes an operation condition selection box 1110, a determination standard display panel 1120, and a configuration change display panel 1130.

The configuration / plan display unit 153 displays a list of each operation condition other than normal in the operation condition selection box 1110 so as to be selectable by a pull-down menu or the like, and allows the operator to select the operation condition to be displayed. , Accept as input. In FIG. 11, the “power outage of the distribution reservoir C equipment”, that is, the condition in which the equipment of the distribution reservoir and the distribution pump facility installed in the distribution reservoir C has a power outage is selected by the operator.

In addition, the configuration / plan display unit 153 displays the determination criteria related to the operation conditions selected in the above-mentioned operation condition selection box 1110 on the determination standard display panel 1120. In the table of the determination standard display panel 1120, a data item used for determination is displayed in column 1121, and a condition for determining that the data item corresponds to the above-mentioned operating conditions is displayed in column 1122.

Further, the configuration / plan display unit 153 displays on the configuration change display panel 1130 the changes in the problem configuration to be added to the problem configuration in normal times under the operation conditions selected in the above-mentioned operation condition selection box 1110. .. In the case of the example of FIG. 11, columns 1131 to 1133 of the table indicate items of the basic index, and columns 1134 to 1136 indicate numerical values to be changed.

The operation planning device 101 of this embodiment presents to the operator the changes in the past demands and judgments of the operator extracted for each operation condition by the processing of the configuration / plan display unit 153 described above, and is necessary. Corrections can be accepted accordingly.

The present invention is not limited to the above-described examples, and includes various modifications. For example, the above-described embodiment has been described in detail in order to explain the present invention in an easy-to-understand manner, and is not necessarily limited to the one including all the described configurations. Further, it is possible to replace a part of the configuration of one embodiment with the configuration of another embodiment, and it is also possible to add the configuration of another embodiment to the configuration of one embodiment. Further, it is possible to add / delete / replace a part of the configuration of each embodiment with another configuration.

Further, each of the above configurations, functions, processing units, processing means and the like may be realized by hardware by designing a part or all of them by, for example, an integrated circuit. Further, each of the above configurations, functions, and the like may be realized by software by the processor interpreting and executing a program that realizes each function. Information such as programs, tables, and files that realize each function can be stored in a memory, a hard disk, a recording device such as an SSD (Solid State Drive), or a recording medium such as an IC card, an SD card, or a DVD.

According to this embodiment, it is possible to formulate an operation plan that appropriately reflects the situation of each plant and the operation know-how.

The description herein reveals at least the following: That is, in the operation planning device of the present embodiment, the problem configuration learning unit may generate the evaluation index by combining the basic indexes by linear calculation and maximum value calculation.

According to this, it is possible to efficiently generate an appropriate evaluation index for the operation planning.

Further, in the operation planning device of the present embodiment, the problem structure learning unit may use an index of robustness of the operation plan with respect to an error of demand forecast as a basic index.

According to this, even if the actual demand deviates significantly from the demand forecast, it is possible to consider that there is no problem in the actual plant operation in response to this as the main point of the operation plan.

Further, the operation planning device of the present embodiment further includes an operation condition extraction unit that extracts the operation conditions of the plant based on the state of the predetermined equipment in the plant indicated by the operation record data, and learns the problem configuration. The unit searches for changes to be added to the configuration of the evaluation index for each of the operational conditions, and the operational planning unit selects the configuration of the evaluation index corresponding to the operational conditions as an objective function. May be.

According to this, it becomes possible to efficiently search for the evaluation index.

Further, the operation plan planning device of the present embodiment may further include a configuration / plan display unit that displays the operation plan and the degree of deviation of the operation plan from the operation range on the predetermined device.

According to this, the user of the operation planning device can easily recognize the drafted operation plan and its contents, and can easily understand the quality and the like.

Further, the operation planning device of the present embodiment may further include a configuration / plan display unit that displays the configuration of the searched evaluation index on a predetermined device and receives a correction instruction for the configuration.

According to this, the evaluation index can be modified to be based on the user's thoughts, actual situation, and the like.

Further, in the operation planning device of the present embodiment, the intake and distribution process of the water supply plant is the target of the operation plan, and the operation range extraction unit is the water intake amount, the water supply amount, the water distribution amount, the distribution reservoir water level, the pump and the valve. The distribution may be extracted for at least one of the number of operation switching operations, the interval, and the time zone.

According to this, in the operation plan for the water supply plant, the basic index can be specified for the key event, and the accuracy of the evaluation index and the operation plan using the index can be improved.

Further, in the operation plan planning device of the present embodiment, the transportation and distribution process of the water supply plant is the target of the operation plan, and the problem composition learning unit determines the degree of agreement between the operation plan and the operation record data related to the period. , Water intake amount, water supply amount, water distribution amount, distribution reservoir water level, difference in operation switching time of pump and valve, may be calculated based on at least one of them.

According to this, it is possible to identify a highly accurate evaluation index for a key event in an operation plan for a water supply plant.

100 Operation control system 101 Operation plan planning device 102 Monitoring control device 103 Sensor 104 Sub-controller 111 Operation range extraction unit 112 Problem configuration learning unit 113 Demand forecast unit 114 Operation plan planning unit 121 Operation record data storage unit 151 Data collection unit 152 Plan output Unit 153 Configuration / plan display unit 201 CPU
202 Memory 203 Media input / output unit 204 Communication control unit 205 Input unit 206 Display unit 207 Peripheral device IF unit 210 Bus 220 Network

Claims (10)

It is a device for making an operation plan of a plant.
An operation range extraction unit that extracts the distribution of the operation range related to a predetermined event from the operation record data related to the plant and determines a basic index indicating the degree of deviation from the operation range for each predetermined event.
By combining the basic indicators of the predetermined event, an evaluation index in the operation plan is generated, and by solving the constraint conditions related to the configuration of the plant and the optimization problem using the evaluation index as the objective function, the past predetermined period can be obtained. A problem composition learning unit that formulates an operation plan, calculates the degree of agreement between the operation plan and the operation record data for the period, and searches for the configuration of the evaluation index that maximizes the degree of agreement.
Calculate the constraint conditions to be satisfied in the operation plan from the predetermined demand forecast value for the plant and the latest operation record data for the plant, and solve the optimization problem using the constraint condition and the searched evaluation index as the objective function. With the operation planning department that formulates the operation plan in
An operation planning device characterized by being equipped with. The problem structure learning unit
The operation planning apparatus according to claim 1, wherein the evaluation index is generated by combining the basic indexes by a linear calculation and a maximum value calculation. The problem structure learning unit
The operation planning apparatus according to claim 1, wherein an index of robustness of an operation plan with respect to an error in demand forecast is used as a basic index. An operation condition extraction unit for extracting the operation conditions of the plant based on the state of the predetermined equipment in the plant indicated by the operation record data is further provided.
The problem structure learning unit searches for changes to be added to the structure of the evaluation index for each of the operating conditions.
The operation planning unit selects the configuration of the evaluation index corresponding to the operation conditions as the objective function.
The operation planning device according to claim 1, wherein the operation planning device is characterized in that. A configuration / plan display unit for displaying the operation plan and the degree of deviation of the operation plan from the operation range is further provided by a predetermined device.
The operation planning device according to claim 1, wherein the operation planning device is characterized in that. The operation planning device according to claim 1, further comprising a configuration / plan display unit that displays the configuration of the searched evaluation index on a predetermined device and receives a correction instruction for the configuration. Targeting the transportation and distribution process of water plants for operation planning
The operation range extraction unit extracts the distribution of at least one of the water intake amount, the water supply amount, the water distribution amount, the distribution reservoir water level, the number of operation switching operations of the pump and the valve, the interval, and the time zone.
The operation planning device according to claim 1, wherein the operation planning device is characterized in that. Targeting the transportation and distribution process of water plants for operation planning
The problem composition learning unit determines the degree of agreement between the operation plan and the operation record data for the period at least one of the water intake amount, the water supply amount, the water distribution amount, the distribution reservoir water level, and the difference in the operation switching time of the pump and the valve. It is calculated based on
The operation planning device according to claim 1, wherein the operation planning device is characterized in that. An operation control system that controls the plant based on the operation plan.
A monitoring control device that collects the measured values from the sensors of the plant and gives control instructions to the sub-controller that controls the plant.
It is an operation planning device that formulates an operation plan that is a control target of the monitoring control device.
The distribution of the operation range related to a predetermined event is extracted from the operation record data which is the measured value for the plant obtained through the monitoring control device, and the basic index indicating the degree of deviation from the operation range is determined for each predetermined event. Range extractor and
By combining the basic indicators of the predetermined event, an evaluation index in the operation plan is generated, and by solving the constraint conditions related to the configuration of the plant and the optimization problem using the evaluation index as the objective function, the past predetermined period can be obtained. A problem composition learning unit that formulates an operation plan, calculates the degree of agreement between the operation plan and the operation record data for the period, and searches for the configuration of the evaluation index that maximizes the degree of agreement.
Calculate the constraint conditions to be satisfied in the operation plan from the predetermined demand forecast value for the plant and the latest operation record data for the plant, and solve the optimization problem using the constraint condition and the searched evaluation index as the objective function. With the operation planning department that formulates the operation plan in
Operation planning device equipped with
An operation control system characterized by including. An information processing device that formulates a plant operation plan
An operation range extraction process that extracts the distribution of the operation range related to a predetermined event from the operation record data related to the plant and determines a basic index indicating the degree of deviation from the operation range for each predetermined event.
By combining the basic indicators of the predetermined event, an evaluation index in the operation plan is generated, and by solving the constraint conditions related to the configuration of the plant and the optimization problem using the evaluation index as the objective function, the past predetermined period can be obtained. A problem configuration learning process that formulates an operation plan, calculates the degree of agreement between the operation plan and the operation record data for the period, and searches for the configuration of the evaluation index that maximizes the degree of agreement.
Calculate the constraint conditions to be satisfied in the operation plan from the predetermined demand forecast value for the plant and the latest operation record data for the plant, and solve the optimization problem using the constraint condition and the searched evaluation index as the objective function. and operational planning process to develop a management plan in,
An operation planning method characterized by executing.

Images